AI Engineer / Lead

We are looking for an AI Engineer to own the technical execution of AI software development lifecycle (AI SDLC). This is a hands-on engineering role focused on building GenAI/LLM-powered processes and products, setting up the frameworks, tooling, and engineering practices.

Skills required:

• 7+ years of software development experience;
• Hands-on experience working within AI-assisted SDLC team;
• Strong developer experience, with a focus on integrating LLM APIs (OpenAI, Anthropic, or similar) or self-hosted models;
• Experience with GenAI orchestration frameworks (e.g., LangChain, LlamaIndex, LangGraph, or equivalents);
• Hands-on experience with LLM-based tools, AI automation platforms, and no-code/low-code AI solutions;
• Experience in measuring and improving model output quality with prompt engineering, and building evaluation harnesses to ;
• Experience with vector databases and retrieval (pgvector, Pinecone or others);
• Solid understanding of the AI SDLC - from experimentation and prototyping through production deployment, monitoring, and iteration;
• Familiarity with MLOps practices: versioning, observability, cost/latency optimization, and CI/CD;
• Awareness of AI safety, guardrails, and responsible-AI practices.

Responsibilities:

• Own the technical execution of the AI SDLC - set up the frameworks, tooling, and engineering practices for building AI features;
• Design and build GenAI systems: agents, RAG pipelines, and integrations with internal and external systems;
• Establish evaluation, testing, and observability so AI output quality can be measured and improved systematically;
• Take AI automations to production, meeting reliability, scalability, and cost targets;
• Define prompt/context-engineering selection process;
• Collaborate with engineers, product, and business stakeholders to turn requirements into working AI solutions;
• Set standards and share AI engineering best practices with the team;
• Stay current with the fast-moving GenAI landscape and evaluate new models, tools, and techniques;
• Upper-intermediate English is a plus.

Will be a plus:

• Experience leading or mentoring a technical team;
• Hands-on experience building and working within shipping GenAI/LLM applications (e.g., RAG pipelines, LLM-powered agents, chatbots, etc)
• Cloud experience (Azure / AWS / GCP) and infrastructure as code;
• Experience with agentic and multi-agent orchestration.

We offer:

• Flexible working arrangements;
• Paid vacations and sick leaves;
• Partial compensation for any sports activity;
• Medical insurance;
• English courses paid by the company;
• Challenging, and fast-growing product;
• Autonomous team structure with a lot of freedom and ownership.