AI Data Engineer

ExlService Holdings, Inc.; Gurgaon; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

ExlService Holdings, Inc. seeks a skilled GenAI/LLM engineer to design and implement AI-enabled applications in a business context. You will build end-to-end LLM pipelines, integrate with enterprise systems, and implement guardrails to ensure high-quality responses.

The role emphasizes Pyton-based backend development, data pipeline work, and collaboration with Data Engineering and MLOps teams to iteratively improve solutions.

Qualifications

• 4–6 years total experience in AI/ML engineering.
• Hands-on GenAI / LLM-based applications experience.

Responsibilities

• Design and develop LLM-based applications using single-agent or simple multi-agent patterns for business use cases.
• Build and maintain RAG pipelines: ingestion, chunking, embeddings, retrieval, response generation.
• Implement prompt engineering techniques (templates, chaining, tool calling).
• Develop backend services/APIs for AI applications using Python frameworks (FastAPI/Flask/Streamlit).
• Integrate AI solutions with enterprise systems, databases, and APIs.
• Apply guardrails and validation checks to reduce hallucinations.
• Collaborate with Data Engineering for data quality and documentation.
• Work with MLOps teams for deployment, monitoring, and iterative improvements.
• Document solutions, reusable components, and best practices.

Tools

LangChain

LangGraph

Azure Databricks

AI frameworks tools

Job description

Key Responsibilities

• Design and develop LLM-based applications using single-agent or simple multi-agent patterns for business use cases
• Build and maintain RAG pipelines: data ingestion → chunking → embeddings → retrieval → response generation
• Implement prompt engineering techniques (prompt templates, chaining, basic tool/function calling)
• Develop backend services/APIs for AI applications using Python frameworks (FastAPI / Flask / Streamlit)
• Integrate AI solutions with enterprise systems, databases, and APIs
• Apply basic guardrails and validation checks to improve response quality and reduce hallucination
• Work with Data Engineering teams to ensure data quality, pipeline efficiency, and proper documentation
• Collaborate with MLOps teams for deployment, monitoring, and iterative improvements
• Document solutions, reusable components, and best practices

Must-Have Skills

Experience

• 4–6 years total experience, with 1+ year hands-on experience in GenAI / LLM-based applications

LLM / GenAI & Agentic Engineering

• Strong hands-on experience with:
  • LLMs (Claude, OpenAI, etc.)
  • RAG pipelines and retrieval optimisation
  • GPT + Agentic AI implementation experience
• Experience with:
  • LangChain, LangGraph, or similar frameworks
  • Agent orchestration and tool-calling architectures
• Deep understanding of:
  • LLM limitations, evaluation, and optimisation strategies

Core Engineering

• Strong Python/Pyspark engineering expertise (production-grade development) with proven API integration experience
• Deep data analysis experience and handling large volume of data
• Fabric/Azure Databricks/Snowflake data engineering integration skills
• Good exposure to:
  • Cloud platforms (Azure/AWS/GCP)
  • SQL
  • Containers, CI/CD, monitoring

Data / AI Foundations (Mandatory)

Prior experience in one or more:

• Data Engineering (ETL/ELT, pipelines, orchestration)
• Data Science / ML lifecycle (especially NLP)
• Analytics engineering / data products

Good-to-Have / Preferred

• Exposure to model fine-tuning (LoRA/PEFT) or prompt optimisation techniques
• Experience with evaluation of LLM outputs (quality, relevance, latency)
• Understanding of enterprise data privacy and security considerations in GenAI
• Exposure to Azure AI / Azure OpenAI / AI Search ecosystems
• Experience working on real client-facing AI solutions or POCs