Job Title: Lead AI Engineer – RAG, GenAI & Vector Search

Experience: 6+ years

Rel Exp: 3+ years

Location: Bangalore

Shift time: 11 to 8 am

Role Overview

AI Engineer with deep, hands-on expertise in building production-grade Retrieval-Augmented Generation (RAG) applications. The ideal candidate has robust experience designing end-to-end RAG pipelines, from multi-format document ingestion and parsing, to retriever design, vector indexing at scale, and rigorous evaluation. You will work closely with data engineers, ML engineers, and product teams to deliver enterprise-grade AI systems that are accurate, scalable, and efficient.

Required Skills & Tech Stack

*RAG (Expertise)

*Document Processing

*Retrieval Frameworks: LangChain; LlamaIndex

*Vector Stores

*Evaluation

*Data Engineering

*Programming: Python (expert level)

*API Integration

*Supporting Tools

Key Responsibilities

- Design, develop, and deploy end-to-end RAG applications, from data ingestion to retrieval and generation.
- Build robust document processing pipelines to parse and extract content from diverse formats – PDF, Word, PPT, images, charts, and tables – using various Python frameworks and OCR/parsing libraries.
- Design and implement chunking strategies tailored to different document types and use cases to optimize retrieval quality.




- Build and fine-tune retrievers using frameworks such as LangChain and LlamaIndex, including hybrid search, re-ranking, and multi-stage retrieval approaches.
- Create, optimize, and manage vector indexes using vector databases (e.g., Milvus, or similar) for scalability, low-latency search, and enterprise-level efficiency.
- Develop and maintain evaluation pipelines for RAG systems using frameworks like RAGAS, tracking metrics such as faithfulness, answer relevancy, context precision/recall, and groundedness.
- Integrate RAG pipelines with internal/external APIs and downstream applications.
- Collaborate with data engineering teams to build scalable data pipelines feeding the RAG ecosystem.
- Optimize system performance across the pipeline, including ingestion, embedding generation, indexing, retrieval, and generation latency.
- Conduct experiments and benchmarking to continuously improve retrieval accuracy and response quality.
- Document architecture, pipelines, and best practices; collaborate cross-functionally with data scientists, product managers, and engineering teams.
- Stay current with advances in LLMs, RAG architectures, vector search, and evaluation methodologies.

Apply Now! Share your profile with us at [email protected].

📌 Lead AI Engineer – RAG, GenAI & Vector Search (Bengaluru)
🏢 KHEYDIGIT
📍 Bengaluru