Artificial Intelligence Developer

EXL; Bengaluru; Hybrid; INR 3,500,000 - 9,000,000; Full time

Job summary

EXL seeks a Senior Manager, RAG/LLM Specialist in Bengaluru to lead the design and optimization of RAG pipelines and model fine-tuning for enterprise-scale deployment.

You will bridge prototype and production, mentor junior analysts in prompt engineering and chunking strategies, and drive evaluation frameworks to ensure high accuracy and efficiency. 4–7 years in ML/AI with LLM experience is expected.

Qualifications

• Bachelor’s or Master’s in CS/Data Science with 4–7 years in ML/AI, including 1+ years with LLMs.
• Deep expertise in advanced RAG (HyDE, document retrieval) and prompt optimization.
• Experience deploying enterprise-scale LLM solutions and pipelines.

Responsibilities

• Design and own multi-stage RAG pipelines ensuring low latency and high relevance.
• Lead fine-tuning initiatives 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.

Skills

RAG/LLM

Prompt optimization

Python

Model fine-tuning

PEFT/LoRA

Education

Bachelor’s or Master’s in CS/Data Science

Tools

LangChain

LlamaIndex

Pinecone

Milvus

Job description

Senior Manager, RAG/LLM Specialist

Experience: 47 Years

Role Overview: Lead the design and optimization of advanced RAG pipelines and model fine[1]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: Bachelor’s/Master’s in CS/Data Science with 4–7 years in ML/AI, including 1+ years specifically working with LLMs.