Senior Manager, RAG/LLM Specialist

EXL

. Design and manage complex, multi-stage RAG pipelines ensuring low latency and high relevance .

Posted 9/23/2026full-timeGurugram • IndiaSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and managing RAG pipelines, fine-tuning open-source models, and developing evaluation frameworks to enhance LLM performance. Proficient in guiding teams on prompt engineering and advanced retrieval strategies within vector databases.

Highest-signal resume keywords

RAG Pipeline ManagementFine-Tuning with PEFT/LoRAPython ProgrammingDeep Expertise in RAGExperience with LLMs

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonPyTorchTensorFlowLangChainLlamaIndexAdvanced Embedding ModelsPrompt OptimizationParameter-Efficient Fine-TuningRAG Pipeline DesignAutomated Evaluation Frameworks

Soft Skills

Team LeadershipMentoring

Tools & Technologies

PineconeMilvusRAGAS

Industry Keywords

Machine LearningArtificial IntelligenceOpen-Source ModelsContext PrecisionRecall

Tech Stack

Tools & technologies

PythonPyTorchTensorflow

About the role

Key responsibilities & impact

Design and manage complex, multi-stage RAG pipelines ensuring low latency and high relevance
Lead fine-tuning initiatives using PEFT/LoRA for open-source models to improve domain-specific task performance
Develop automated evaluation frameworks such as RAGAS to measure LLM accuracy, context precision, and recall
Architect metadata filtering and hybrid search strategies within vector databases such as Pinecone and Milvus
Guide junior analysts in prompt engineering, chunking strategies, and code quality

Requirements

What you’ll need

Bachelor’s/Master’s in CS/Data Science with 4–7 years in ML/AI, including 1+ years specifically working with LLMs
Python
PyTorch/TensorFlow
LangChain
LlamaIndex
Advanced embedding models
Deep expertise in advanced RAG, including HyDE and parent-document retrieval
Prompt optimization
Parameter-efficient fine-tuning
Experience with PEFT/LoRA and open-source models