Senior Manager

EXL; Bengaluru; On-site; INR 3,000,000 - 5,200,000; Full time

Job summary

EXL is seeking a Senior Manager, RAG/LLM Specialist to design and optimize advanced RAG pipelines and refine model deployment for enterprise-scale LLMs.

You will own end-to-end RAG solutions, lead PEFT/LoRA fine-tuning, and drive automated evaluation frameworks to ensure high accuracy and recall. Mentorship of junior analysts and hands-on guidance on prompts and chunking will be part of the role.

Qualifications

• Bachelor’s/Master’s in CS/Data Science with 5+ years in ML/AI.

Responsibilities

• Design and own multi-stage RAG pipelines with low latency and high relevance.
• Lead fine-tuning (PEFT/LoRA) for open-source models 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 (Pinecone, Milvus).
• Mentor junior analysts on prompt engineering, chunking, and code quality.

Skills

Python

PyTorch/TensorFlow

LangChain

LlamaIndex

Embedding models

RAG HyDE

Prompt optimization

PEFT fine-tuning

Vector search

Education

CS/Data Science degree

Tools

LlamaIndex

Pinecone

Milvus

Job description

Role Overview: Senior Manager, RAG/LLM Specialist

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

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.

Qualifications:

• Qualifications: Bachelor’s/Master’s in CS/Data Science with 5+ years in ML/AI, including 1+ years specifically working with LLMs.

Required Skills:

• 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.