Lead Generative AI / RAG Architect

Inspired Infotech LLC.; Hyderabad; On-site; INR 4,500,000 - 7,000,000; Full time

Job summary

Inspired Infotech LLC. in Hyderabad, India, seeks a seasoned architect to define secure, scalable GenAI and RAG platforms and set engineering standards across client projects.

You will lead a team of GenAI engineers, review designs for quality and security, and advise clients on model and platform choices while staying current with the AI landscape.

Qualifications

• 6–10 years in software or data engineering with GenAI/LLM focus.
• 2+ years leading GenAI/LLM projects and teams.
• Expertise in retrieval, embeddings and vector search.
• Experience with Bedrock / Azure OpenAI / Vertex AI on at least two platforms.

Responsibilities

• Define architecture and standards for enterprise GenAI and RAG platforms.
• Lead and mentor a team of GenAI engineers.
• Review designs and code for quality and security.
• Advise clients on model and platform selection.
• Track AI landscape and evolve reference architectures.

Skills

GenAI leadership

LLM/GenAI

Retrieval & embeddings

Vector search

AWS Bedrock

Azure OpenAI

Vertex AI

Team leadership

Python

Kubernetes

Tools

LlamaIndex

OpenSearch

Azure AI Search

pgvector

Langfuse

Job description

Define architecture and standards for enterprise generative-AI and RAG solutions across our client portfolio, and lead a team of GenAI engineers.

What you will do

• Architect secure, scalable RAG and LLM platforms
• Define standards for retrieval, evaluation, guardrails and LLMOps
• Lead and mentor a team of GenAI engineers
• Review designs and code for quality and security
• Advise clients on model and platform selection
• Track the AI landscape and evolve our reference architectures

What you will bring

• 6-10 years of software or data engineering experience, including 2+ years leading LLM/GenAI work
• Deep expertise in retrieval, embeddings, vector search and evaluation
• Experience on at least two of Amazon Bedrock, Azure OpenAI / AI Foundry and Vertex AI
• Team leadership experience

Nice to have

• Fine-tuning experience
• Enterprise search background
• AI governance knowledge (EU AI Act, ISO/IEC 42001)

Tech stack

Python, Amazon Bedrock, Azure AI Foundry, Vertex AI, LlamaIndex, OpenSearch, Azure AI Search, pgvector, Langfuse, Kubernetes

What we offer

• A permanent, full-time role
• Enterprise projects for clients in the US and worldwide
• Hands-on work across AI, cloud and modern engineering
• A friendly, collaborative team
• Clear paths for professional growth

Work authorization

This role is based in Hyderabad, India. Applicants must be legally eligible to work in India.