Senior Backend AI Engineer (LLM & RAG)

We are looking for an experienced Backend / AI Engineer with strong expertise in building production-grade LLM applications and document intelligence solutions.

The role requires a combination of advanced Python backend development and hands-on experience with LLM systems, RAG pipelines, structured outputs, evaluation, and production deployment.

Key Responsibilities

• Design and develop production-grade LLM applications with a clear separation between model-driven logic and deterministic backend components.
• Build and improve RAG pipelines, including document chunking, hybrid search, reranking, and retrieval quality measurement.
• Work on context engineering, prompt and instruction design.
• Implement structured LLM outputs using JSON schemas, function calling, and response validation.
• Develop solutions using embeddings and vector databases/search technologies such as ChromaDB, pgvector, and Qdrant.
• Build and maintain LLM evaluation pipelines, including evaluation datasets, metrics, regression testing, and tools such as DeepEval or similar frameworks.
• Perform failure analysis and ensure reproducibility of LLM-based systems.
• Optimize LLM solutions across quality, cost, and latency.
• Develop and maintain backend services and REST APIs.
• Implement asynchronous and long-running LLM workflows using task queues.
• Write automated tests, including tests for non-deterministic AI components.
• Work with relational databases, caching systems, containers, and production infrastructure.

Required Experience & Skills

AI / LLM Engineering

• Hands-on experience building production LLM applications.
• Strong understanding of architectural boundaries between LLM components and deterministic application logic.
• Practical experience with:
• RAG architectures;
• chunking strategies;
• hybrid retrieval;
• reranking;
• retrieval quality evaluation;
• context engineering;
• prompt / instruction design;
• structured outputs;
• JSON schemas and function calling;
• embeddings and vector search.
• Experience with OpenAI API.
• Experience with LLM evaluation, evaluation datasets, metrics, regression testing, and tools such as DeepEval or equivalents.
• Understanding of LLM failure modes and practical failure analysis.
• Ability to optimize AI systems for quality, cost, and latency.

Backend Engineering

• Advanced Python development skills.
• Strong knowledge of:
• Python typing;
• asynchronous programming;
• production-grade project architecture.
• Experience with Django and Django Ninja, or strong experience with FastAPI.
• Experience designing and developing REST APIs.
• Experience with Celery and task queues for long-running operations.
• Strong experience with pytest, including testing non-deterministic components.

Data & Infrastructure

• Strong practical knowledge of PostgreSQL, including:
• schema design;
• indexes;
• query execution plans;
• query optimization.
• Experience with Redis and SQLite.
• Experience with Docker, Linux, and Git.
• Basic understanding of CI/CD.

Education

• Higher education in Computer Science, Applied Mathematics, or a related technical field is preferred.
• Strong knowledge of algorithms and data structures.

Nice to Have

• Production experience with Java, especially Spring and JDBC.
• Experience with Oracle.
• Knowledge of C, C++, C#, CMake, Google Test.
• JavaScript experience.
• Experience with AI-assisted development tools and workflows such as:
• Claude Code;
• Codex;
• Cursor;
• agentic development workflows;
• iterative test-driven development with AI coding assistants.

Seniority

We are looking for an engineer capable of working independently in a production environment, making technical decisions, diagnosing problems, and taking ownership of implemented solutions.