Senior AI Engineer

EXL; Dadri; On-site; INR 900,000 - 1,500,000; Full time

Job summary

EXL is seeking an Agentic AI / Gen AI Engineer to design, build, and deploy AI-driven agentic systems and LLM-powered applications in India. You will prototype to production, be hands-on with prompt engineering, and work across the full lifecycle from design to deployment.

You will work with LangChain, LangGraph, and other frameworks, build LLM applications, and implement RAG pipelines using vector databases.

Qualifications

• 2-5 years of experience in AI/ML engineering with hands-on Generative AI and LLM-based systems.
• Proficient in Python and API integration (REST/GraphQL).
• Hands-on with prompt engineering techniques and embedding/semantic search concepts.
• Experience with at least one vector database and cloud deployment.

Responsibilities

• Design and build agentic AI workflows using LangChain, LangGraph, AutoGen, CrewAI, or similar.
• Develop Generative AI applications leveraging LLMs (OpenAI, Anthropic, open-source models).
• Implement RAG pipelines with vector databases for search and retrieval.
• Design, test, and refine prompts for accuracy and cost-efficiency.
• Architect and maintain embedding pipelines for semantic search.
• Collaborate with data engineering to integrate structured/unstructured data.
• Fine-tune or adapt pre-trained models for domain use cases.
• Monitor, evaluate, and improve model outputs with guardrails and tests.
• Deploy and maintain AI solutions in production (API, containers, cloud).
• Document architecture and prompt libraries for the team.

Skills

Python programming

Prompt engineering

LLM integration

API integration (REST/GraphQL)

Cloud platforms (AWS/Azure/GCP)

Vector databases

Model deployment

MLOps basics

Education

Bachelor's/Master's degree in Computer Science, Engineering, Data Science, or related field

Tools

LangChain

LangGraph

AutoGen

CrewAI

Pinecone

Weaviate

Milvus

Qdrant

FAISS

ChromaDB

Docker

Kubernetes

Job description

We are looking for an Agentic AI / Gen AI Engineer to design, build, and deploy AI-driven agentic systems and LLM-powered applications. The ideal candidate has hands‑on experience with prompt engineering, retrieval‑augmented generation (RAG), and vector database implementations, and is comfortable working across the full lifecycle from prototyping to production deployment.

Key Responsibilities

• Design and develop agentic AI workflows using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar
• Build and optimize Generative AI applications leveraging LLMs (OpenAI, Anthropic, open‑source models like Llama/Mistral)
• Implement RAG pipelines integrating vector databases (Pinecone, Weaviate, Milvus, Qdrant, FAISS, or ChromaDB)
• Design, test, and refine prompts for accuracy, consistency, and cost‑efficiency across use cases
• Architect and maintain embedding pipelines for semantic search and knowledge retrieval
• Collaborate with data engineering teams to integrate structured/unstructured data sources into AI pipelines
• Fine‑tune or adapt pre‑trained models where applicable for domain‑specific use cases
• Monitor, evaluate, and improve model outputs using evaluation frameworks and guardrails
• Deploy and maintain AI solutions in production environments (API integration, containerization, cloud deployment)
• Document architecture, prompt libraries, and technical decisions for team knowledge sharing
• Required Skills & Experience
• 2-5 years of experience in AI/ML engineering, with recent hands‑on exposure to Generative AI and LLM‑based systems
• Practical experience with prompt engineering techniques (few‑shot, chain‑of‑thought, prompt chaining)
• Working knowledge of agentic AI frameworks (LangChain, LangGraph, AutoGen, CrewAI, or similar)
• Hands‑on experience with at least one vector database (Pinecone, Weaviate, Milvus, Qdrant, FAISS, ChromaDB)
• Strong Python programming skills; familiarity with API integration (REST/GraphQL)
• Understanding of embedding models and semantic search concepts
• Experience with cloud platforms (AWS/Azure/GCP) for AI model deployment
• Familiarity with LLM orchestration, tool‑calling, and function‑calling paradigms
• Exposure to MLOps practices (model versioning, monitoring, CI/CD for ML) is a plus

Good to Have

• Experience fine‑tuning open‑source LLMs
• Knowledge of evaluation frameworks (RAGAS, LangSmith, etc.)
• Prior experience in BFSI, healthcare, or other regulated domains
• Familiarity with Docker/Kubernetes for containerised deployments

Qualifications

• Bachelor's/Master's degree in Computer Science, Engineering, Data Science, or related field