RAG/LLM Specialist_ Manager/Sr. Manager

EXL; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

EXL in Bengaluru seeks a Senior Manager RAG/LLM Specialist to lead the design, optimization, and enterprise deployment of advanced Retrieval-Augmented Generation (RAG) solutions and LLM-based applications.

The role requires hands-on work with RAG pipelines, PEFT/LoRA, embeddings, vector databases, prompt engineering, and evaluation frameworks, guiding productionization and cross-functional collaboration to deliver scalable GenAI capabilities across the enterprise.

Qualifications

• 47 years of experience in AI/ML, Data Science, NLP, or Software Engineering.
• Hands-on experience with LLM/GenAI.
• Strong Python programming skills.
• Experience with RAG pipelines and retrieval models.
• Knowledge of LangChain and/or LlamaIndex.

Responsibilities

• Design and manage multi-stage RAG pipelines focusing on relevance, accuracy, scalability, and low latency.
• Lead LLM fine-tuning using PEFT, LoRA/QLoRA.
• Work with open-source foundation models to improve domain performance.
• Design retrieval strategies including hybrid search, semantic search, metadata filtering, reranking, HyDE, and parent-document retrieval.
• Develop automated evaluation frameworks using RAGAS.
• Architect and optimize vector database solutions (Pinecone, Milvus, FAISS, Weaviate, Qdrant).
• Lead prompt engineering and optimization across GenAI use cases.
• Collaborate with data, engineering, and product teams to productionize LLM solutions.
• Mentor junior team members on RAG architecture, chunking, prompts, evaluation, and code quality.
• Drive best practices around LLM development, observability, testing, and performance.

Skills

AI/ML experience

Python

RAG / Retrieval-Augmented Generation

LangChain / LlamaIndex

Embedding models

Prompt engineering

LLM fine-tuning (PEFT/LoRA)

PyTorch / TensorFlow

Vector databases

Tools

Pinecone

Milvus

FAISS

Weaviate

Qdrant

Chroma

Elasticsearch/OpenSearch

Job description

Senior Manager RAG/LLM Specialist

Experience: 47 Years
Function: Generative AI / Machine Learning / LLM
Employment Type: Full-time

Role Overview

We are looking for a Senior Manager RAG/LLM Specialist to lead the design, optimization, and enterprise deployment of advanced Retrieval-Augmented Generation (RAG) solutions and LLM-based applications.

The ideal candidate will have strong hands-on experience in RAG pipelines, LLM fine-tuning, embeddings, vector databases, prompt engineering, and GenAI evaluation frameworks, with the ability to take solutions from prototype to production at enterprise scale.

Key Responsibilities

• Design and manage complex, multi-stage RAG pipelines focused on high relevance, accuracy, scalability, and low latency.
• Lead LLM fine-tuning initiatives using PEFT, LoRA/QLoRA, and other parameter-efficient techniques.
• Work with open-source foundation models to improve domain-specific performance.
• Design advanced retrieval strategies including hybrid search, semantic search, metadata filtering, reranking, HyDE, and parent-document retrieval.
• Develop automated evaluation frameworks using tools such as RAGAS to measure context precision, context recall, response quality, and overall LLM performance.
• Architect and optimize vector database solutions using technologies such as Pinecone, Milvus, FAISS, Weaviate, or Qdrant.
• Lead prompt engineering and optimization initiatives across GenAI use cases.
• Work closely with data, engineering, and product teams to productionize LLM solutions.
• Mentor junior team members on RAG architecture, chunking strategies, prompt engineering, evaluation, and code quality.
• Drive best practices around LLM application development, observability, testing, and performance optimization.

Required Skills

• 47 years of experience in AI/ML, Data Science, NLP, or Software Engineering, with at least 1+ year of hands-on LLM/GenAI experience.
• Strong programming skills in Python.
• Hands-on experience with RAG / Retrieval-Augmented Generation.
• Strong knowledge of LangChain and/or LlamaIndex.
• Experience with advanced embedding models and vector search.
• Strong understanding of prompt engineering and prompt optimization.
• Hands-on experience with LLM fine-tuning, PEFT, LoRA/QLoRA.
• Experience with PyTorch and/or TensorFlow.
• Experience with vector databases such as Pinecone, Milvus, FAISS, Weaviate, Qdrant, Chroma, Elasticsearch/OpenSearch.
• Knowledge of RAG evaluation and RAGAS.
• Exposure to OpenAI, Anthropic, Hugging Face, or other LLM platforms/APIs.

Good to Have

• Experience with HyDE, parent-document retrieval, reranking, hybrid search, query expansion, and contextual retrieval.
• Experience deploying LLM applications in production.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Knowledge of LLM observability and evaluation tools.
• Experience mentoring engineers or leading GenAI initiatives.