Data Scientist

Neurealm; Gurugram District; On-site; INR 1,200,000 - 2,000,000; Full time

Job summary

Neurealm is seeking an AI/ML Engineer to design, develop, and deploy ML and Generative AI solutions in a dynamic team. You will build RAG pipelines, create AI agents using LangChain, LangGraph, and other frameworks, and integrate them with enterprise APIs and data sources.

You will craft prompts, tool-calling workflows, and output pipelines for LLM applications while optimizing models for accuracy, latency, and cost.

Qualifications

• Proficiency in Python and ML fundamentals required.
• Strong knowledge of NLP and LLM concepts.
• Experience with RAG pipelines and embeddings.
• Familiarity with AI agent frameworks and tool-calling workflows.
• Experience evaluating models for accuracy and latency.
• Exposure to multi-model orchestration and monitoring.

Responsibilities

• Design and deploy ML/G AI solutions for business problems.
• Build RAG pipelines using vector databases and knowledge sources.
• Develop AI agents with LangChain/LangGraph and related tools.
• Integrate agents with enterprise APIs, databases, and services.
• Develop prompts, tool calls, and structured outputs for LLM apps.
• Fine-tune and optimize LLM-powered applications for cost and latency.
• Implement data preprocessing and ML training workflows.
• Collaborate with product, software, and subject matter experts.
• Monitor performance and drive continuous improvements.

Skills

Python

Machine Learning fundamentals

Natural Language Processing

Generative AI & LLMs

Prompt Engineering

RAG

Embeddings / Semantic search

Model evaluation & validation

Tools

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

Job description

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