Senior Fullstack and AI/ML Engineer

ENIOR FULLSTACK & AI/ML ENGINEER

We're looking for a Senior Fullstack & AI/ML Engineer to implement AI solutions that automate operational business processes. We need someone who can own solutions end-to-end — from prototype and architecture through production — and is responsible for the full product stack: UI, backend, data, and the AI layer.

IIN THIS ROLE YOU WILL

1. Develop frontend interfaces in React for client products and internal tools.
2. Design, build, and maintain backend services, REST APIs, webhooks, and third-party integrations in Node.js/TypeScript and/or Python; design ETL pipelines.
3. Design, build, and optimize ML models for real business problems.
4. Develop and integrate AI solutions based on GPT, Claude, and Gemini into production applications.
5. Build AI assistants and solutions for intelligent automation of document processing (structured extraction, OCR), application verification, customer support, and other business processes.
6. Design and implement Retrieval-Augmented Generation (RAG) solutions and agentic workflows.
7. Integrate solutions with ERP/CRM and corporate systems.
8. Work with PostgreSQL/Supabase, MongoDB, and vector databases (Pinecone, Weaviate).
9. Develop and maintain asynchronous tasks (Celery); work with Docker, Redis, and CI/CD pipelines.
10. Evaluate and improve AI model performance through experiments, A/B testing, and results analysis.
11. Deploy and maintain solutions in production — monitoring, troubleshooting, fixes, and ongoing development.
12. Make architectural decisions and set technical standards.

What we're looking for:

• 3+ years of commercial React development experience (production-level).
• 3+ years of commercial experience building AI/ML solutions (NLP, LLM).
• 1.5+ years of hands-on experience integrating LLMs into production.
• Practical experience with LLM APIs (OpenAI/Anthropic/Google), structured outputs, function calling / tool use, RAG.
• Experience with prompt engineering and frameworks such as LangChain / LangGraph / LlamaIndex.
• Experience with structured extraction from documents and free-form text (contracts, reports, correspondence).
• Experience building stateful pipelines with state tracking in a database.
• Experience with PostgreSQL / Supabase and MongoDB.
• Experience integrating with ERP/CRM or other corporate systems.
• Hands-on experience with Docker, Git, Redis, Celery, and CI/CD.
• Experience deploying and supporting production systems (monitoring, troubleshooting).
• Ability to both build architecture from scratch and independently navigate existing code, extending it safely without breaking production logic.
• Strong understanding of software architecture, clean code principles, and SOLID.
• English: Upper-Intermediate (B2) or higher.
• Native Ukrainian.
• Bachelor's or Master's degree in Computer Science, Applied Mathematics, Data Science, or a related field.

Nice to have:

• Experience with AWS, Azure, or Google Cloud Platform (including SageMaker, Bedrock, or Azure OpenAI).
• Experience with microservices and Kubernetes.
• Experience deploying to client environments (self-hosted solutions, not only shared cloud).
• n8n / Make or similar automation platforms.
• NumPy/Pandas for data processing.
• Fine-tuning open-source models (LLaMA).
• Familiarity with automated testing.

• Experience building internal enterprise systems.

  Experience working with sensitive client data and selecting an LLM provider based on data processing requirements (DPA) is a plus.

   

Engagement format: project-based / part-time / full-time — to be discussed depending on scope and workload.

• To be considered for this role, you must be able to work under the FOP (sole proprietor) model.