This is a remote position.
- Provide technical leadership for Python-based GenAI services
- Design backend architecture for LLM products including routing, retrieval, memory and evaluation flows
- Build and optimise Python microservices exposing GenAI capabilities (FastAPI, Pydantic)
- Drive RAG pipeline design using LangChain and LangGraph
- Define ingestion, chunking and embedding workflows for enterprise knowledge systems
- Integrate vector databases (Pinecone, Chroma, Weaviate)
- Establish standards for prompt lifecycle management, token strategy, and model selection
- Collaborate with frontend and platform teams to ensure smooth API consumption
- Lead evaluation cycles, latency reduction, and production-readiness measures
- Promote best practices in code quality, observability, DevOps, and cloud deployment
Requirements
- 6+ years of Python engineering experience with strong backend foundations
- Proven commercial experience building GenAI or LLM-centric systems
- Hands-on expertise with FastAPI, Pydantic, LangChain, LangGraph
- Strong understanding of embeddings, similarity search, and vector databases
- Experience running GenAI workloads in production environments
- Ability to lead engineers, make architectural decisions, and coordinate delivery
- English at B2+ level for daily collaboration
- Knowledge of LangSmith, TruLens, or other evaluation frameworks
- Experience with Azure OpenAI, Anthropic, or HuggingFace Hub
- Background in conversational orchestration or tool-calling architectures
- Ability to coach prompt engineers and data engineers
Benefits
- Solid, competitive salary
- Work in multinational environment on international projects
- Comprehensive healthcare
- Long-term B2B contract with stable project pipeline
- Fully remote model
