Agentic/AI engineers with Claude/code/LLM skills1

EXL Talent Acquisition Team; Dadri; On-site; INR 3,000,000 - 7,000,000; Full time

Job summary

EXL Talent Acquisition Team seeks an experienced engineer to design and deliver agentic LLM solutions across business domains such as customer support and document intelligence.

You will build end-to-end RAG pipelines, implement prompt engineering, and develop production APIs (FastAPI/Flask/Streamlit) integrating with enterprise data sources. Strong Python, cloud, and collaboration with Data Engineering are essential.

Qualifications

• Hands-on experience with LLMs including Claude and understanding capabilities/limitations.
• Practical experience with RAG, embeddings, vector databases, semantic search, retrieval quality.
• Experience with orchestration stacks (LangChain, LangGraph, Hugging Face).
• Experience building agentic workflows including tool calling and function calling.
• Exposure to coding-agent workflows (Claude Code) is a plus.

Responsibilities

• Design and build agentic LLM solutions across domains.
• Build end-to-end RAG pipelines with data ingestion, embeddings, and retrieval orchestration.
• Implement prompt engineering and orchestration for cost/latency optimization.
• Develop production services/APIs (FastAPI/Flask/Streamlit) and integrate with data sources.
• Apply guardrails to reduce hallucinations and enforce policy constraints.
• Collaborate with Data Engineering and MLOps for data quality and CI/CD.

Skills

LLM/GenAI delivery

Python

Communication

Problem solving

Cloud platforms

Education

Bachelor's or Master’s in CS/DS

Tools

Claude

FAISS

Pinecone

ChromaDB

LangChain

LangGraph

Hugging Face

FastAPI/Flask/Streamlit

Job description

Key Responsibilities

• Design and build agentic LLM solutions (single- and multi-agent patterns) to solve real business problems across domains (e.g., customer support, document intelligence, knowledge retrieval).
• Build RAG pipelines end-to-end: data ingestion → chunking/embeddings → vector search → retrieval orchestration → response synthesis, with measurable quality.
• Implement prompt engineering and prompt orchestration (prompt chains, tool-calling, function calling), including prompt iteration and cost/latency optimisation.
• Develop production services/APIs for LLM applications (e.g., FastAPI/Flask/Streamlit) and integrate with enterprise systems and data sources.
• Apply guardrails to reduce hallucinations, enforce policy constraints, and ensure safe tool usage; implement evaluation strategies for LLM and RAG outputs.
• Collaborate with Data Engineering teams to ensure data quality, governance, and documentation standards, and with MLOps/Platform teams for CI/CD, monitoring, and reliable deployments.
• Create and maintain technical documentation, solution design artefacts, and reusable components for faster delivery and consistent engineering practices.

Must-Have Skills

5 to 12 years total experience, with hands-on LLM/GenAI delivery experience (preferably 1–3+ years building production-grade LLM apps).

LLM / GenAI & Agentic Engineering

• Hands-on experience with LLMs including Claude (Anthropic) and other leading models; strong understanding of capabilities, limitations, and use-case fit.
• Practical experience with RAG, embeddings, vector databases (e.g., FAISS/Pinecone/ChromaDB), semantic search, and retrieval quality evaluation.
• Experience with frameworks/tools such as LangChain, LangGraph, Hugging Face, or equivalent orchestration stacks.
• Experience building agentic workflows including tool calling/function calling; familiarity with “agentic architecture” concepts is valued.
• Exposure to Claude Code or similar coding-agent workflows is a plus (agentic coding that can work across codebases, run tests, and iterate).

Core Engineering

• Strong Python engineering skills (production-grade coding, testing, packaging, API development).
• Solid understanding of cloud platforms (Azure/AWS/GCP) and deployment basics (containers, CI/CD, monitoring).
• Strong communication skills—ability to translate business needs into technical solutions and articulate trade-offs clearly.

Mandatory Background (Non-negotiable)

• Prior experience in Data Engineering or Data Science:
  • Data pipelines / ETL / ELT / orchestration, or
  • ML/NLP modelling lifecycle, experimentation, evaluation, or
  • Analytics engineering and data product delivery.

Good-to-Have / Preferred

• Fine-tuning approaches (e.g., LoRA/PEFT), prompt tuning, few-shot strategies, and model evaluation methods.
• Experience with enterprise-grade privacy/security considerations for GenAI solutions (data handling, redaction, access control).
• Experience with Azure stack components often used in GenAI (e.g., Azure AI Search / Azure OpenAI) is beneficial.

Education

Bachelor’s or Master’s degree in Computer Science, Data Engineering, Data Science, Information Systems, or related fields (or equivalent practical experience).