Jobs Lviv, ML / AI

Company Overview

Robots & Pencils is an applied AI engineering firm building the next frontier of business architecture. We design and ship AI co-workers that integrate into enterprise operations and deliver measurable results for our clients. We're all in on AWS, combining deep UX capability with senior engineering talent to get AI into production fast and keep it there.
We’ve earned the trust of leaders across Consumer Products and Retail, Education, Energy, Financial Services, Healthcare, and Manufacturing and more, and earned a reputation as the nimble alternative to traditional global systems integrators. Founded in 2009, with delivery centers in Canada, the United States, Eastern Europe, and Latin America, we are smaller, faster, and more senior by design. Our teams average 15+ years of experience. We move fast, sweat the details, and build things that actually ship.
 

Position Overview

We’re looking for a Principal AI Engineer to define and drive the technical direction of our AI/ML systems. This role is ideal for a deeply experienced engineer who leads from the front — shaping architecture at the system level, solving the hardest problems, and raising the bar for how AI gets built and operated across the organization.

In this role, you will work on a cross-functional team, setting AI architecture standards, leading complex system design and implementation challenges, and solving integration problems that require both deep expertise and broad systems thinking. You’ll partner closely with leadership to define the AI roadmap and make high-stakes technical decisions that shape how our AI work scales across clients and over time.

Why This Role Matters

At Robots & Pencils, we design AI systems for a human world. Our name says it all. Robots and pencils means engineering paired with creativity, because every agent we ship has to work for real people in real workflows. That balance is baked into how we operate.

Every role here contributes directly to that mission. Here, you shape how AI systems integrate into enterprise operations, how teams move at real velocity, and how products create measurable impact for clients and the people they serve. We ship production-ready AI in 30 to 45 days. That pace demands people who take ownership, lead with craft, and care deeply about what they put their name on.

What You’ll Do

Craft & Delivery

• Define AI architecture and technical strategy, and lead implementation across the full lifecycle from design through production
• Build scalable ML platforms, pipelines, and workflow orchestration that support model development and event-driven, asynchronous operations at scale
• Architect and build LLM-powered systems, including prompt engineering, function/tool calling, multi-agent orchestration, RAG patterns, vector databases, embeddings, and streaming responses
• Design and develop APIs and backend services that integrate AI capabilities with enterprise systems and third-party platforms
• Lead model development, optimization, and the path from research to production, ensuring promising approaches translate into reliable, production-ready systems
• Ensure AI reliability, security, and scalability across deployed systems, including logging, monitoring, and debugging in production environments
• Bring an AI-forward mindset to your daily work, using tools like Claude, Cursor, and other modern AI assistants to ship higher-quality work at pace

Collaboration & Communication

• Co-define the AI roadmap with leadership, operating as a peer in strategic technical conversations
• Communicate complex technical concepts clearly to engineering and non-engineering stakeholders alike, translating depth into decisions others can act on
• Engage with product, engineering, and data teams to align AI work with broader business priorities

Leadership & Influence

• Define and champion AI engineering standards that shape how the organization builds and operates AI systems
• Mentor across the organization, shaping engineering culture and developing the next generation of technical leaders
• Own high-stakes architectural decisions that carry significant organizational and cross-engagement weight
• Drive technical vision — defining not just what gets built, but how AI engineering evolves at R&P over time

What You’ll Bring

• 9+ years of professional software engineering experience, with 5+ years focused on AI/ML systems in production and deep, hands-on expertise with generative AI development
• Expert software engineering background (Python or similar) with strong design sensibilities for distributed, scalable, and maintainable systems
• Deep experience designing distributed systems and event-driven architectures that underpin production AI workloads
• Deep expertise with cloud platforms, with mastery of AWS services and AWS GenAI offerings
• Proven track record architecting and shipping complex agentic systems in production across multiple teams or engagements
• Mastery of AI frameworks and orchestration tools, with clear judgment on when to adopt versus build
• Deep experience with evaluation frameworks and observability tools for LLM apps, including establishing these practices where they don't yet exist
• Deep expertise in AI safety, responsible AI principles, prompt injection defenses, PII handling, and AI governance and compliance in production
• Extensive experience designing RAG architectures: chunking strategies, embedding models, vector databases, and advanced retrieval techniques
• API and systems design experience, including architecting and integrating with internal and third-party services at scale
• Advanced cost optimization expertise: token economics, caching strategies, model routing, quantization
• Strong working knowledge of Docker, Kubernetes, and cloud-native AI architecture patterns
• Expertise in MLOps and AI infrastructure, including model versioning, monitoring, deployment automation, and reproducibility
• Demonstrable, day-to-day usage and expert command of AI-forward coding tools such as Claude Code and Cursor
• Track record of technical leadership and mentoring at an organizational level, with influence that extends beyond the immediate team
• Excellent problem-solving and stakeholder communication skills, with the ability to navigate the most ambiguous technical and business challenges with sound judgment

You’ll Do Well Here if You Are

• A doer. You see something broken and fix it. You'd rather move on clarity than wait for certainty.
• A fast learner who knows you don't know everything. The AI landscape changes weekly. You're senior enough to know better and curious enough to keep learning anyway.
• Direct in a way that makes the work better. You give honest feedback. You'd rather have the hard conversation than blow smoke.
• Obsessed with craft. You know genius is in the details. You ship exceptional, not perfect, and you don't put your name on work you wouldn't stand behind.
• Built for ownership. You honor commitments, admit mistakes fast, and back your teammates when a decision costs something. No handoffs, no finger-pointing.
• All in. You treat clients' businesses like your own. You take the work seriously without taking yourself seriously.
• Resourceful when the budget, timeline, or team is tight. Constraints don't slow you down. They sharpen you.
• Glad to be in the room with people who care as much as you do. Our teams average fifteen-plus years of experience. We hire people who push each other to do better work.

We Offer

• 20 days of paid vacation.
• 15 days of unpaid vacation.
• All official public holidays off.
• 5 paid sick days without a doctor's certificate.
• Medical insurance.
• Military draft deferment (reservation) support.
• Cooperation under a gig-contract.

N-iX is seeking a motivated Trainee AI Engineer to join our dynamic team and working on the AI solution for the global biopharmaceutical company. This role offers an excellent opportunity to work with cutting-edge AI technologies to help create innovative solutions that provide engaging and insightful experiences for users. The ideal candidate will have a basic understanding of machine learning and a keen interest in developing AI applications. While our project uses Palantir Foundry, prior experience with it is a plus, but not mandatory.

Requirements:

• Currently pursuing or recently completed a Bachelor's degree in Computer Science, Artificial Intelligence, or a related field.
• Basic programming skills in Python.
• Familiarity with machine learning concepts and frameworks like TensorFlow or PyTorch.
• Interest in natural language processing and computer vision.
• Willingness to learn and work with cloud services (AWS, Azure, or GCP).
• Ability to work collaboratively in a team environment.
• Strong problem-solving skills.
• Upper Intermediate+ knowledge of the English language.
• Ukrainian language - advanced or higher.

Responsibilities:

• Assist in developing AI solutions, including chatbots and computer vision applications.
• Support the integration of AI solutions into existing platforms and workflows.
• Help optimize machine learning models for performance, accuracy, and user engagement.
• Contribute to building and optimizing retrieval-augmented generation (RAG) systems and vectorized databases.
• Monitor and evaluate the performance of AI applications, identifying areas for improvement.
• Stay informed about developments in AI, machine learning, and related fields to contribute to innovative solutions.
• Assist in developing and maintaining documentation related to AI models and applications.
• Work with data engineers to support data preparation for training and fine-tuning models.
• Support the implementation of security measures to protect sensitive information processed by AI applications.

Nice to have:

• Experience with AI projects through coursework or personal projects.
• Understanding of RESTful APIs and how applications integrate.
• Familiarity with version control tools like Git.

We are expanding our talent pool of Python Machine Learning Engineers to support upcoming international projects across various industries, including FinTech, Healthcare, Retail, Manufacturing, and SaaS.

While there is no immediate project assignment, selected candidates will become part of our network and will be among the first to be considered when new opportunities matching their expertise become available.

Our machine learning projects typically involve designing, training, deploying, and optimizing predictive models, recommendation systems, computer vision, NLP, and other AI-driven solutions using modern Python technologies and MLOps practices.

We are expanding our talent pool of Python AI Engineers (LLM & GenAI) to support upcoming international projects focused on Generative AI, Large Language Models, AI Agents, and intelligent automation.

While there is no immediate project assignment, selected candidates will become part of our network and will be among the first to be considered when new AI opportunities matching their expertise become available.

Our AI projects typically involve designing and developing LLM-powered applications, Retrieval-Augmented Generation (RAG) systems, AI Agents, intelligent workflows, and enterprise AI solutions using modern Python technologies.

🔹Who we are!

At Levi9, we are passionate about what we do. We love our work and together in a team, we are smarter and stronger. We are looking for skilled team players who make change happen. Are you one of these players?

🔹About the project

You will join a dynamic, cross-functional AI team building AI prototypes, from classic ML to advanced LLM applications such as Text-to-SQL and complex RAG systems. Our goal is to engage our customers with advanced AI solutions.

🔹Responsibilities

• Design and deploy predictive ML models (e.g., decision trees, random forests, gradient boosting) for analytics and feature engineering.
• Develop recommendation systems using collaborative and content-based filtering techniques.
• Build and enhance RAG systems, including embedding pipelines, managing vector databases, and integrating LLMs.
• Implement text-to-SQL capabilities, allowing users to query relational databases naturally using LangChain or similar technologies.
• Work alongside data engineers to ensure robust data pipelines and high-quality datasets for training and inference.
• Collaborate with Product Owners and UX Designers to align AI features with user needs and business goals.
• Continuously research, test, and apply cutting-edge algorithms and technologies to boost model performance and scalability.
• Monitor and improve production models, ensuring reliability, performance, and compliance with ethical standards.
   

🔹Requirements

• Experience: 4+ years in AI/ML, specifically building and deploying production-level ML models.
• Classic ML: Solid skills with decision trees, random forests, and gradient boosting methods (scikit-learn, XGBoost).
• Recommender Systems: Proven experience in collaborative and content-based recommendation algorithms.
• RAG & LLM Development: Hands-on expertise with retrieval-augmented generation systems, vector databases (Pinecone, Weaviate), and frameworks like LangChain or LlamaIndex.
• Text-to-SQL: Experience developing natural-language-to-SQL solutions using frameworks like LangChain.
• Programming & Data: Advanced Python proficiency, strong SQL skills, and familiarity with Pandas and NumPy.
• Cloud & MLOps: Knowledge of deploying models on AWS, Azure, or GCP, and familiarity with CI/CD and MLOps tools (MLflow, Kubeflow).
• Communication: Comfortable in Agile teams with excellent English communication skills.

🔹Will be a plus

• Experience with Docker and Kubernetes.
• Familiarity with advanced embedding techniques and optimizing similarity searches.
• Background in deep learning frameworks such as TensorFlow or PyTorch.
• Knowledge of ethical AI practices and data privacy standards.

🔹 Our customer's stack
Core — Python 3.13, LangGraph and LangChain for agent orchestration, AWS Bedrock for inference, retrieval, and runtime (AgentCore, Knowledge Bases, Guardrails), Pydantic for schema enforcement, CloudFormation for infrastructure.
Quality — pytest across unit, integration, and e2e tiers with a coverage gate, ruff, mypy and pyright, promptfoo for prompt and output evaluation. We hold agent code to the same bar as any other production system.

🔹9 reasons to join us:

1. Today we're working with the technology of tomorrow.
2. We don't wait for a change. We are the change.
3. We're experts in creating experts (Levi9 academy, Lead9 program for leaders).
4. No micromanagement. We are free birds with a clear understanding of what high performance is!
5. Learning in Levi9 never stops (unlimited Udemy for business, meetups, English courses, Professional trainings).
6. Here you can train your body and mind.
7. We've gathered the best locations - comfortable, cozy and pet-friendly offices in Kyiv (5 minutes from Olimpiyska subway station) and Lviv (5 minutes from the Opera Theatre) with regular offline internal events
8. We have master's degree in work-life balance.
9. We are actively supporting Ukraine with constant donations and volunteering
    

🔹Simple steps to get this job

Click the APPLY NOW button and leave your contacts!

We are looking for a Prompt Spec Engineer who will define how our AI systems communicate, reason, and deliver high-quality outputs across products powered by LLMs.
 

You will be responsible for designing prompt/spec architectures, building evaluation systems, and ensuring that AI responses are consistent, reliable, and production-ready across RAG systems, AI agents, and automation workflows.

What you will do:
 

• Design and evolve prompt/spec architecture for AI products, LLM services, RAG systems, and AI agents, defining prompt structures, model behavior rules, response formats, and quality criteria.
• Develop, optimize, and adapt prompts for different LLMs and use cases, considering output quality, context limitations, cost, and system stability.
• Build and maintain AI evaluation processes including test scenarios, golden datasets, regression testing, and A/B experiments for LLM performance measurement.
• Analyze AI outputs, identify root causes of issues (hallucinations, missing context, retrieval problems, incorrect or unsafe responses), and define improvements.
• Collaborate with AI Engineers and Product Managers to implement prompt solutions into production systems, RAG pipelines, AI agents, and automation workflows, translating business needs into technical specifications.
• Work with LLM evaluation and monitoring tools (such as PromptFoo, Langfuse, and similar solutions) to track metrics, prompt versions, response quality, and system performance.
• Create and maintain structured documentation: prompt specs, evaluation frameworks, usage guidelines, limitations, and best practices for safe and reliable AI behavior.

What we expect from you:
 

• 2+ years of experience in LLM-related roles such as Prompt Engineering, AI Product Operations, AI Evaluation, or similar.
• Hands-on experience designing and optimizing prompts for different LLMs with a strong understanding of model behavior, strengths, and limitations.
• Experience building prompt/spec systems including prompt structure design, behavior rules, response formatting, testing, and versioning.
• Strong experience in AI evaluation: test case design, output analysis, issue detection, and iterative improvement of model performance.
• Understanding of RAG systems, AI agents, structured outputs, tool calling, and principles of reliable LLM system design.
• Ability to collaborate with engineering and product teams, translate business requirements into AI specifications, and document solutions clearly and consistently.
• Upper-Intermediate (B2+) English 
   

What we offer

• Competitive compensation depending on experience
• Work on production-level AI systems (LLMs, RAG, AI agents, automation workflows)
• Office-based work in Lviv with the possibility of a hybrid schedule.
• Direct impact on AI product quality and system behavior
• Access to modern LLM tools and evaluation frameworks
• Professional growth in a fast-moving AI-focused environment
• Opportunity to shape prompt engineering standards inside the company
• Relocation support for candidates from other cities, including assistance with moving and adaptation in Lviv.

About the role:
We’re looking for a GenAI Engineer to design and build production-grade AI capabilities, including intelligent agents, LLM-powered features, and workflow automation. In this role, you’ll collaborate closely with product, engineering, and design teams to integrate cutting-edge AI technologies into a large-scale, customer-facing product.

You’ll join a US-based team developing one of the world’s leading enterprise video platforms, used by thousands of organizations worldwide for live streaming, virtual events, online training, webinars, and other interactive experiences.
Requirements:

• Strong software engineering background (Python preferred)
• Proven track record of building production-grade GenAI applications
• Hands-on experience with LLMs, RAG, AI agents, vector databases, and AI orchestration frameworks
• Practical experience with OpenAI, Anthropic, Google Gemini, Amazon Bedrock, or similar AI platforms
• Strong system design and problem-solving skills
• Upper-Intermediate English (B2+) or higher 

Nice to Have

• Experience with AWS and cloud-native applications
• Exposure to MCP, AI automation, or multimodal AI 

Responsibilities

• Build AI-powered features using modern LLMs
• Develop AI agents, tool-calling workflows, and RAG systems
• Integrate AI capabilities with enterprise products through APIs and MCP
• Optimize prompts, model performance, and AI quality
• Collaborate with Product, Engineering, and Design teams to deliver production-ready AI solutions 

What We Offer

• Work on production AI features with real user impact in a flexible, Agile, multinational team where innovation and collaboration drive everything we do
• Continuous learning and professional growth alongside top talent in the global tech industry
• Hybrid work model, combining remote work with time in our Lviv office
• Daily collaboration with native English speakers, providing a natural opportunity to strengthen your English in a professional environment
• 18 working days of paid vacation, 10 working days of paid sick leave, and 11 paid Ukrainian public holidays