We are looking for an AI Production Engineer for one of our client to take ownership of a live, enterprise-grade Generative AI application as it moves from development into production. This is an ownership role—not a research, strategy, or demo-building position.
Key Responsibilities
System Ownership: Keep the live GenAI application running reliably in production.
LLMOps & Monitoring: Track model performance, token usage, latency, costs, and manage prompt versioning.
RAG & Retrieval: Continuously improve vector search, chunking, and retrieval accuracy.
Feature Execution: Turn business requests from HR, Finance, Sales, and Ops into production features and workflow integrations.
Model Benchmarking: Evaluate current LLMs, APIs, and frameworks for performance and cost efficiency.
Key Requirements
2–3 years of experience with at least one production GenAI/LLM application (copilot, chatbot, enterprise AI tool).
Hands-on proficiency in Python, LLM APIs, RAG/Vector DBs, and Agent workflows.
Basic familiarity with LLMOps/MLOps, cloud platforms, and enterprise API integrations.
Ownership Mindset: Ability to take messy problems, build solutions, ship them, and manage them post-launch.

📌 AI Production Engineer (India)
🏢 SaarthiOS
📍 India