Role Overview
We are looking for a Senior AI / GenAI Engineer to architect, build, and deploy production-grade LLM applications, RAG pipelines, and multi-agent workflows. You will collaborate with cross-functional teams to integrate enterprise-grade AI solutions into our scalable backend and cloud infrastructure.
Key Responsibilities
- GenAI Development: Architect end-to-end RAG systems and multi-agent workflows using LangChain, LangGraph, and vector databases.
- Model Evaluation & Optimization: Fine-tune models and track performance metrics using frameworks like RAGAS, BLEU, and ROUGE.
- Backend Architecture: Design and maintain robust RESTful APIs in Python using FastAPI to serve AI features.
- Deployment & Cloud: Package and deploy scalable models using Docker and AWS services (Bedrock, SageMaker, EC2, S3) via CI/CD pipelines.
Required Qualifications
- 1+ years of dedicated professional experience delivering GenAI/LLM solutions in production.
- Technical Stack: Deep proficiency in Python, SQL, PyTorch/TensorFlow, Scikit-Learn, FastAPI, and Hugging Face.
- GenAI Frameworks: Advanced hands-on experience with LangChain, LangGraph, OpenAI APIs, and vector databases (Pinecone, FAISS).
- Infrastructure: Demonstrated experience with Docker containerization and AWS infrastructure (SageMaker, Bedrock, EC2, S3).
Pay: ₹1,800,000.00 - ₹2,000,000.00 per year
Application Question(s):
- Are you available to attend a single-round, face-to-face interview this Monday or Tuesday at the SunLife office in Sector-62, Gurugram?
- Are you currently located in Delhi-NCR (Delhi/Gurgaon/Noida/Faridabad/Ghaziabad) and comfortable working in a hybrid setup (Gurugram office)?
- What is your current employment status and notice period?
- What is your current CTC and expected CTC?
- Hands-on GenAI Experience: Do you have 1+ years of hands-on experience building production RAG pipelines, AI agents (using LangChain or LangGraph), and FastAPI endpoints in Python?
Work Location: In person
