Office location : Gurgaon

Role: Data Scientist 

Experience: 3–5 Years 

Key Responsibilities 

Design, develop, and deploy Machine Learning and Generative AI solutions. 

Build Retrieval-Augmented Generation (RAG) pipelines using vector databases and enterprise knowledge sources. 

Develop AI agents using Agentic AI frameworks such as LangGraph, LangChain, CrewAI, or similar technologies. 

Integrate AI agents with enterprise APIs, tools, databases, and external services. 

Develop prompts, tool-calling workflows, and structured output pipelines for LLM applications. 

Fine-tune, evaluate, and optimize LLM-powered applications for accuracy, latency, and cost. 

Implement data preprocessing, feature engineering, and ML model training workflows. 

Work with structured and unstructured datasets to solve business problems. 

Collaborate with Product Managers, Software Engineers, and Subject Matter Experts to deliver AI-driven features. 

Monitor model and agent performance and participate in troubleshooting and continuous improvements. 

Write clean, maintainable, and well-tested Python code following engineering best practices. 

Stay updated with the latest advancements in Machine Learning, LLMs, and Agentic AI technologies. 

Required Technical Skills 

Core Skills 

Strong proficiency in Python 

Machine Learning fundamentals 

Natural Language Processing (NLP) 

Generative AI and Large Language Models (LLMs) 

Prompt Engineering 

Retrieval-Augmented Generation (RAG) 

Embeddings and semantic search 

Model evaluation and validation techniques 

Agentic AI Frameworks 

Hands-on experience with LangChain and LangGraph 

Experience building AI agents with tool calling and workflow orchestration 

Familiarity with CrewAI, AutoGen, Semantic Kernel, or similar frameworks 

Understanding of agent memory, planning, state management, and multi-step reasoning 

ML & AI Libraries 

Scikit-learn 

XGBoost or LightGBM 

PyTorch or TensorFlow 

Hugging Face Transformers 

OpenAI, Anthropic, Gemini, Bedrock, Azure OpenAI, or similar LLM APIs 

Vector databases such as Pinecone, FAISS, ChromaDB, Weaviate, Milvus, or OpenSearch 

Data & Cloud 

SQL and relational databases 

Experience with AWS, Azure, or GCP 

Docker and containerized deployments 

Basic CI/CD knowledge 

MLflow or similar experiment tracking tools 

REST APIs/FastAPI for AI model deployment 

Good to Have 

Experience building production-ready AI or LLM applications. 

Exposure to multi-agent systems and workflow orchestration. 

Knowledge of Model Context Protocol (MCP). 

Experience with AI evaluation frameworks and guardrails. 

Understanding of MLOps and model monitoring. 

Experience with fine-tuning techniques such as LoRA, PEFT, or QLoRA. 

Experience with document processing, OCR, or document intelligence. 

Experience in legal, regulatory, financial, healthcare, or publishing domains.