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




· Solid 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)
Experience in supporting AWS based application is add on

📌 AI engineer (Gurugram)
🏢 Virtusa
📍 Gurugram