RAG LLM Specialist

EXL; Bengaluru; Hybrid; INR 4,200,000 - 5,600,000; Full time

Job summary

EXL in Bengaluru is seeking an experienced ML/AI lead to design and optimize advanced RAG pipelines and oversee model fine-tuning workflows for enterprise-scale LLM deployment.

You will guide junior analysts in prompt engineering, chunking strategies, and code quality, while championing robust evaluation and hybrid search using vector databases.

Qualifications

• 4–7 years in ML/AI including 1+ years with LLMs.
• Experience with RAG, PEFT/LoRA and open-source models.
• Proven ability to design scalable ML pipelines and evaluate them.

Responsibilities

• Design and manage multi-stage RAG pipelines with low latency and high relevance.
• Lead fine-tuning initiatives (PEFT/LoRA) to improve domain-specific task performance.
• Develop automated evaluation frameworks to measure LLM accuracy, context precision, and recall.
• Architect metadata filtering and hybrid search strategies within vector databases like Pinecone or Milvus.
• Mentor junior analysts in prompt engineering, chunking strategies, and code quality.

Skills

Prompt engineering

Mentoring juniors

System design

Project leadership

LLM proficiency

Education

Bachelor's/Master's in CS/Data Science

Tools

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

Pinecone

Milvus

PEFT/LoRA

Job description

Role Overview

Lead the design and optimization of advanced RAG pipelines and model fine tuning processes. Bridge the gap between prototype and enterprise-scale LLM deployment.

Key Responsibilities

• Pipeline Ownership: Design and manage complex, multi-stage RAG pipelines ensuring low latency and high relevance.
• Model Optimization: Lead fine-tuning initiatives (PEFT/LoRA) for open-source models to improve domain-specific task performance.
• Advanced Evaluation: Develop automated evaluation frameworks (e.g., RAGAS) to continually measure LLM accuracy, context precision, and recall.
• Vector Strategy: Architect metadata filtering and hybrid search strategies within vector databases (e.g., Pinecone, Milvus).
• Team Mentorship: Guide junior analysts in prompt engineering, chunking strategies, and code quality.

Required Skills & Qualifications

• Tech Stack: Python, PyTorch/TensorFlow, LangChain, LlamaIndex, advanced embedding models. GenAI Skills: Deep expertise in advanced RAG (HyDE, parent-document retrieval), prompt optimization, and parameter-efficient fine-tuning.
• Qualifications: Bachelors/Masters in CS/Data Science with 4–7 years in ML/AI, including 1+ years specifically working with LLMs.