Vacancy description
UFO Engineering builds custom software solutions for international clients, and we're growing our AI development practice. We're looking for an AI Engineer who can build LLM-powered features and integrate AI technologies into real-world products, from prototype to production.
You will work with modern Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents and AI APIs, helping turn business requirements into reliable AI-powered software solutions.
Skills
3+ years of commercial software development experience with Python
Hands-on experience building features with LLM APIs such as OpenAI, Anthropic, Gemini or similar
Practical experience with RAG, including embeddings, chunking, retrieval and vector databases such as pgvector, Qdrant or Pinecone
Understanding of prompt design, structured outputs and tool/function calling
Experience building REST APIs with FastAPI, Django or similar frameworks
Experience with SQL and/or NoSQL databases
Experience with Git and Docker
Understanding of LLM limitations and approaches to improving the quality and reliability of AI-generated responses
Upper-Intermediate English (spoken and written)
Will be plus
Experience with LangChain, LlamaIndex, LangGraph or similar frameworks
Experience building AI agents and multi-step AI automation workflows
Experience evaluating LLM output quality, including evals, test datasets or LLM-as-judge
Experience with AI model evaluation and comparison
Classic Machine Learning or NLP background
Experience with cloud AI services such as AWS Bedrock, Azure OpenAI or Vertex AI
Frontend experience with React or similar technologies
Experience delivering AI-powered features end to end
Duties
Design and build LLM-powered features such as chatbots, RAG systems, document processing solutions and AI agents
Integrate LLMs, AI APIs and other AI services into existing web applications
Develop production-ready AI solutions with attention to response quality, reliability, cost and latency
Design and improve RAG pipelines, including document processing, embeddings, retrieval and generation
Implement structured outputs, tool calling and multi-step AI workflows
Evaluate new LLM models, AI tools and frameworks and recommend appropriate solutions for projects
Monitor and evaluate the quality of AI-generated responses and improve system performance
Work closely with developers, project managers and clients to turn business requirements into working AI solutions
Develop, test, refactor and document production code
We offer
Really flexible work schedule
Completely remote work format
15 days of paid vacation per year + 5 sick days
Accounting support for FOP and partial tax coverage
Ability to truly influence the company and shape internal processes
English courses twice a week – fully covered by the company
Opportunity to grow into a lead or mentor if you enjoy teaching and guiding others
Zero bureaucracy and open communication with anyone in our alien team – from interns to the CEO
And our main advantage (in the humble opinion of the recruiter) – a loyal and friendly team 💙
