Description :

Key Responsibilities :

- Design and develop AI / Machine Learning models including LLM pipelines, RAG, Agent-based systems and Vector database integration.

- Understand and optimize latency across RAG and model calls.

- Deploy AI models into production using MLOps frameworks and CI/CD pipelines.

- Optimize models for scalability, reliability, and performance.

- Experience in incident response and troubleshooting for AI systems, including resolving slow RAG performance, poor retrieval quality, API rate-limit issues, vector store indexing failures, and agent infinite loops.

- Ability to diagnose and manage cost-related issues, including unexpected spend spikes caused by inefficient prompts, retries, or misconfigured AI workloads.

- Collaborate with Developers, DevOps, and application teams to build AI enabled systems.

Required Skills :

- Strong understanding of modern LLM technologies, RAG patterns, and agent frameworks.

- Solid experience with Python.

- Experience with observability tools, traces, logs, metrics (OpenTelemetry preferred)

- Hands-on experience with FastAPI, Gunicorn containerised deployments

- Familiarity with LangChain, LlamaIndex, or similar AI orchestration frameworks

- Knowledge of vector databases (Pinecone, AWS Knowledgebase, Chroma, etc.)

- Experience with cloud platforms (AWS).

- Experience with CI/CD pipelines and MLOps practices.

- Handle OpenAI Outages (fallbacks to smaller models)