You will join a team building next-generation AI-powered products based on Large Language Models. The project focuses on transforming LLM prototypes into scalable, secure, and production-grade systems. The role covers the full AI lifecycle – from architecture and backend development to infrastructure, monitoring, and cost optimisation.
responsibilities :
Build and maintain production-grade LLM systems (including RAG, semantic search, embeddings, vector databases).
Design and develop APIs and microservices in Python (e.g. FastAPI).
Develop and maintain CI/CD pipelines for models (LLMOps/MLOps).
Deploy and manage infrastructure in AWS (Lambda, ECS/EKS, S3, API Gateway, CloudWatch).
Implement containerisation (Docker) and orchestration (Kubernetes).
Monitor model quality (latency, drift, hallucinations, cost efficiency).
Collaborate closely with Data Science, ML, Data Engineering and Product teams.
requirements-expected :
Strong Python skills with experience building production APIs.
Hands-on experience deploying LLM-based systems in production.
Practical knowledge of RAG, embeddings, vector databases, and semantic search.
Experience with AWS and scalable backend system design.
Solid understanding of Docker, Kubernetes and CI/CD.
Proven ability to move from PoC to stable production solutions.
offered :
Opportunity to work on advanced AI systems with real product impact.
Strong influence on architecture and technology decisions.
Collaboration with an experienced Data & AI team in an international environment.
