Senior AI Engineer, Agentic and RAG Systems

About the role

We are looking for a hands‑on Senior AI Engineer to design, build, and operate production‑grade Generative AI systems. You will own end‑to‑end delivery of agentic workflows, Retrieval‑Augmented Generation (RAG) pipelines, and LLM‑backed services that serve real users under strict SLAs.

Key responsibilities

• Design and implement agent orchestration (graph/state, conditional routing, tool calling, memory, checkpointing) using LangGraph, LangChain or equivalent frameworks.
• Build full‑stack RAG pipelines: chunking, embeddings, vector stores, hybrid retrieval, reranking, caching and grounded synthesis.
• Develop production‑ready Python/FastAPI services with async handling, SSE streaming, session management and robust error contracts.
• Instrument systems with tracing and evaluation harnesses (MLflow, OpenTelemetry, etc.) to monitor accuracy, cost and regression.
• Ship containers on Docker and Kubernetes (EKS/AKS/GKE) via CI/CD pipelines with test, evaluation and canary gates.
• Drive LLM cost‑engineering through model routing, prompt optimisation, token accounting and build‑vs‑buy decisions.
• Apply GenAI safety and governance measures: hallucination control, prompt‑injection defence, PII handling and human‑in‑the‑loop where required.
• Collaborate with data engineering on semantic layers and pipelines (PySpark, SQL) as needed.

Required profile

• 5+ years of software engineering experience, including at least 2 years delivering production LLM or agentic systems.
• Strong proficiency in Python and FastAPI (async, REST, SSE).
• Hands‑on production experience with LangChain/LangGraph or comparable stacks (LlamaIndex, AutoGen, MCP).
• Deep knowledge of RAG components: embeddings, chunking, hybrid retrieval, reranking and caching.
• Experience with vector databases such as Pinecone, Weaviate, pgvector, OpenSearch or Databricks Vector Search.
• Practical experience deploying on Kubernetes and Docker in cloud environments (AWS preferred).
• Familiarity with observability tools (MLflow, LangSmith, OpenTelemetry) and CI/CD systems (GitHub Actions, Jenkins).

Required skills

• Python
• FastAPI
• LangChain / LangGraph
• LlamaIndex, AutoGen, MCP
• Embeddings, chunking, hybrid retrieval, reranking, caching
• Pinecone, Weaviate, pgvector, OpenSearch, Databricks Vector Search
• AWS Bedrock, OpenAI, Azure OpenAI, Anthropic
• Kubernetes, Docker
• AWS cloud engineering
• MLflow, LangSmith, OpenTelemetry
• GitHub Actions, Jenkins
• PySpark, SQL