Manager, RAG/LLM Specialist

Ex; Gurugram District; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Ex is seeking an Applications Development Engineer to lead the design and optimization of RAG pipelines and model finetuning, bridging prototype and enterprise-scale LLM deployment.

Role emphasizes mentorship, advanced evaluation, and hybrid search strategies, with a focus on PEFT/LoRA, LangChain, and embedding models within a Python-based ML stack.

Qualifications

• 4–7 years in ML/AI with 1+ years working with LLMs.

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
• Team Mentorship: Guide junior analysts in prompt engineering, chunking strategies, and code quality.

Skills

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

Embedding models

Education

BSc/MSc CS or Data Science

Tools

PEFT/LoRA

Job description

• Job Role Application Development-Applications Development Engineering
• Experience (In Years) 6-9

Job Description

Role Overview:Lead the design and optimization of advanced RAG pipelines and model finetuning processes. Bridge the gap between prototype and enterprise-scale LLM deployment.

Responsibilities

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
• Team Mentorship:Guide junior analysts in prompt engineering, chunking strategies, and code quality.

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.