We are hiring a hands-on AI engineer to design, build and deploy production-grade enterprise AI solutions for a leading financial markets infrastructure organisation. The role works closely with business and technology teams to convert high-value use cases into secure, scalable applications.

Key responsibilities:
Build and productionise Retrieval-Augmented Generation (RAG) pipelines, LLM-based agents and agentic workflows.
Develop Python services, APIs, data ingestion and transformation pipelines, and integrations with enterprise systems.
Work with vector or graph databases and improve retrieval quality through chunking, embeddings, hybrid search and reranking.
Implement evaluation, prompt and model guardrails, access controls, auditability, observability and performance monitoring.
Containerise and deploy services using Docker and Kubernetes; contribute to CI/CD and MLOps/LLMOps practices.
Partner with users through discovery, prototyping,



rollout and adoption while retaining hands-on production ownership.

Candidate profile:
3 to 6 years of relevant experience, with recent hands-on ownership of production AI or GenAI applications.
Solid Python development, API engineering and data pipeline skills.
Demonstrated experience with production RAG, LLM agents or agentic AI workflows.
Working knowledge of vector databases such as Pinecone, Milvus, Qdrant, Weaviate or pgvector.
Exposure to cloud or on-premise deployments, Docker, Kubernetes, CI/CD, observability and security controls.
Transparent communication and ability to work with business stakeholders in a regulated setting.

Qualification: BE/BTech/MCA in Computer Science, IT, Data Science or an allied engineering discipline.

📌 Forward Deployed Ai Engineer – Deputy Manager Mumbai
🏢 Avant Garde
📍 Mumbai