GenAI Engineer - LLM/RAG
Description
Role Overview :
We are looking for a GenAI Engineer / AI-ML Engineer for our Insurance domain client at Gurgaon.
Location : Gurugram (Hybrid)
Employment Type : Full-Time
Experience : 4 to 6 Years
Preference : Noida/NCR Local Candidates Only
Key Responsibilities :
- Design, develop, and deploy scalable AI/ML and Generative AI solutions.
- Build and optimize RAG (Retrieval-Augmented Generation) pipelines using modern frameworks and vector databases.
- Develop LLM-powered applications leveraging prompt engineering, AI agents, and multi-agent workflows.
- Fine-tune, evaluate, and monitor machine learning and deep learning models.
- Build REST APIs and backend services for AI applications.
- Design data preprocessing, feature engineering, and model evaluation pipelines.
- Integrate structured and unstructured data sources to deliver contextual AI solutions.
- Collaborate with cross-functional teams including Data Engineering, DevOps, and Product teams.
- Ensure scalability, reliability, and performance of AI applications in production environments.
Tech Stack & Requirements :
- Programming : Python, SQL.
- Frameworks : FastAPI, Scikit-learn, TensorFlow, PyTorch, Keras.
- GenAI/NLP : LLMs, Prompt Engineering, RAG Architectures, Agentic AI, LangChain, LangGraph, OpenAI APIs, Hugging Face, LangSmith.
- Vector Databases : Pinecone, FAISS.
- Cloud/DevOps : AWS (EC2, S3, SageMaker, Bedrock), Docker, Git, JIRA, CI/CD.
Skills
- Agentic AI
- AI
- API
- AWS
- CI/CD
- Cloud
- Data Engineering
- Deep Learning
- DevOps
- Docker
- EC2
- FAISS
- FastAPI
- Feature Engineering
- Generative AI
- Git
- Hugging Face
- Jira
- Keras
- LangChain
- LangGraph
- LangSmith
- LLM
- Machine Learning
- Model Evaluation
- NLP
- OpenAI
- Pinecone
- Prompt Engineering
- Python
- PyTorch
- RAG
- REST
- S3
- SageMaker
- scikit-learn
- SQL
- TensorFlow
- Vector Databases
Sign in to read and join the discussion.