Ai & Ml Development Lead

EXL Service; Haryana; On-site; INR 2,000,000 - 4,200,000; Full time

Job summary

EXL Service is seeking an AI/ML engineer to design and deliver enterprise-grade AI solutions using LLMs and modern frameworks. You will build applications with LangChain, LangGraph, and multi-agent architectures, and drive end-to-end development from problem definition to production deployment.

Collaborating with product, engineering, and data teams, you will optimize AI pipelines, embeddings, RAG, and prompt engineering for production use on cloud platforms such as Azure, AWS, or GCP.

Qualifications

• 4–6 years of experience in AI/ML engineering or related roles.
• Strong Python programming skills (mandatory).
• Experience with LLMs, LangChain, LangGraph, and agent frameworks.
• Hands-on knowledge of multi-agent systems and MCP (or similar protocols).
• Understanding of RAG, embeddings, prompt engineering, and LLM orchestration.
• Experience in deploying AI solutions on cloud platforms (Azure/AWS/GCP).
• Strong communication skills and ability to work with cross-functional teams.
• Experience with MLOps practices, APIs, and production deployments.

Responsibilities

• Develop and deploy LLM-based applications using RAG, embeddings, and prompt engineering.
• Build and manage multi-agent systems and workflows using LangGraph, MCP, or similar frameworks.
• Design scalable AI pipelines, APIs, and integrations for production use.
• Optimize performance, cost, and reliability of AI systems in production.
• Collaborate with product, engineering, and data teams to deliver business impact.

Skills

Python programming

LLMs

Prompt engineering

Multi-agent systems

Communication skills

Tools

LangChain

LangGraph

MCP

Cloud platforms (Azure/AWS/GCP)

MLOps

Job description

Job Description

• Design and deliver enterprise-grade AI solutions using LLMs and modern AI frameworks
• Build and optimize applications using LangChain, LangGraph, and multi-agent architectures
• Drive end-to-end development lifecycle from problem definition to production deployment
• Collaborate with cross-functional teams to translate business needs into AI solutions

Responsibilities

• Develop and deploy LLM-based applications using RAG, embeddings, and prompt engineering
• Build and manage multi-agent systems and workflows using LangGraph, MCP, or similar frameworks
• Design scalable AI pipelines , APIs, and integrations for production use
• Optimize performance, cost, and reliability of AI systems in production
• Collaborate with product, engineering, and data teams to deliver business impact

Qualifications

• 4–6 years of experience in AI/ML engineering or related roles
• Strong Python programming skills (mandatory)
• Experience with LLMs, LangChain, LangGraph, and agent frameworks
• Hands-on knowledge of multi-agent systems and MCP (or similar protocols)
• Understanding of RAG, embeddings, prompt engineering, and LLM orchestration
• Experience in deploying AI solutions on cloud platforms (Azure/AWS/GCP)
• Strong communication skills and ability to work with cross-functional teams
• Experience with MLOps practices, APIs, and production deployments