Overview

We are seeking an experienced GenAI / AI-ML Engineer to design, develop, and deploy scalable Generative AI and Machine Learning solutions.

Responsibilities

• GenAI & Agentic Systems: Develop LLM-powered applications utilizing prompt engineering, AI agents, and multi-agent workflows (LangChain, LangGraph).
• RAG Pipelines: Build, optimize, and evaluate Retrieval-Augmented Generation (RAG) pipelines using modern vector databases and frameworks like RAGAS.
• Backend Integration: Write robust Python code and build high-performance REST APIs using FastAPI to support AI models in production.
• ML/DL Engineering: Design end-to-end data preprocessing, feature engineering, fine-tuning, and model evaluation pipelines using Scikit-learn, PyTorch, TensorFlow, and Keras.
• Cloud & DevOps: Containerize applications using Docker and deploy scalable models on AWS (SageMaker, Bedrock, EC2, S3) with CI/CD integration.
• Collaboration: Partner with Data Engineering, DevOps, and Product teams to ensure reliability, security, and performance of production environments.

Qualifications

• Programming & Backend: Strong proficiency in Python, SQL, and framework expertise with FastAPI.
• GenAI Stack: Hands-on experience with OpenAI APIs, Hugging Face, LangChain, LangGraph, LangSmith, and vector databases (Pinecone, FAISS).
• Evaluation Metrics: Practical experience with evaluation frameworks (RAGAS, BLEU, ROUGE) and semantic search architectures.
• Cloud Infrastructure: Solid background with AWS services (EC2, S3, SageMaker, Bedrock), Docker, and Git.
• Availability: Immediate joiners or candidates currently serving their notice period based in Noida/NCR.
• Are you based in Noida/NCR and available as an immediate joiner (or currently serving your notice period)?
• Do you have at least 1 year of hands-on experience building GenAI applications using LangChain, LangGraph, or multi-agent workflows?
• Which vector databases and RAG evaluation tools have you used in production (e.g., Pinecone, FAISS, RAGAS)?
• How many years of experience do you have building production REST APIs using FastAPI in Python?