Senior Full Stack AI Engineer

Wadhwani Foundation; Bengaluru; On-site; INR 4,200,000 - 6,600,000; Full time

Job summary

Wadhwani Foundation is seeking a core engineer to own end-to-end GenAI pipelines and production-grade AI systems that serve learners across India and global markets. You will build and deploy GenAI/LLM systems, RAG architectures, and multimodal content automation within a lean team.

You should have 5–7 years of engineering experience with demonstrable GenAI deployments, strong Python and FastAPI skills, and hands-on experience with LangGraph, LlamaIndex, LangChain, and cloud platforms.

Qualifications

• 5–7 years of total engineering experience with demonstrable GenAI production deployments.
• Strong Python expertise; experience with FastAPI, async patterns, and REST API design.
• Hands-on with LLM frameworks: LangGraph, LlamaIndex, LangChain, or equivalent.
• Experience with multimodal AI — image/audio/video generation, ASR, TTS, or voice models.
• Solid understanding of RAG architectures, vector stores, embeddings, and retrieval strategies.
• Comfortable with cloud-native deployments on GCP, Azure, Runpod.
• Excellent communication and cross-functional collaboration skills.
• Ownership mindset — you take a feature from ideation to production.

Responsibilities

• Design and ship production GenAI systems end-to-end — from backend pipelines to user-facing interfaces
• Build and maintain RAG architectures and multi-agent orchestration systems using LangGraph, LlamaIndex, and related frameworks
• Develop multimodal AI pipelines for audio, image, and video content generation and automation
• Architect scalable APIs using FastAPI / Python; integrate with cloud platforms (Azure, AWS)
• Collaborate with internal teams and external vendors to operationalize AI features as shared services
• Write clean, well-tested, production-ready code with strong engineering discipline
• Contribute to architectural decisions and help define team best practices
• Well versed with AI driven development tools – Cursor, Claude, Copilot, Replit, etc.

Skills

GenAI production deployments

Python

FastAPI

REST API design

Async programming

LLM frameworks (LangGraph, LlamaIndex,

Multimodal AI

RAG architectures

Cloud deployments

Communication & collaboration

Education

B.Tech / M.Tech / MS in relevant field

Tools

LangGraph

LlamaIndex

LangChain

Azure

AWS

GCP

Job description

ABOUT THE ROLE

You will be a core engineer on Wadhwani Foundation's lean AI team, building production-grade AI systems that serve millions of learners across India and global markets. This is not a research role — you will own end-to-end delivery of GenAI pipelines, agentic platforms, and multimodal content automation systems that create measurable social impact at scale.

WHAT YOU'LL WORK ON

GenAI & LLM Systems

Production deployment of LLMs — Gemini, Azure OpenAI, Groq, open‑source models at scale

RAG & Agentic Pipelines

LangGraph multi‑agent orchestration, LlamaIndex RAG, MCP integrations

RESPONSIBILITIES

• Design and ship production GenAI systems end‑to‑end — from backend pipelines to user‑facing interfaces
• Build and maintain RAG architectures and multi‑agent orchestration systems using LangGraph, LlamaIndex, and related frameworks
• Develop multimodal AI pipelines for audio, image, and video content generation and automation
• Architect scalable APIs using FastAPI / Python; integrate with cloud platforms (Azure, AWS)
• Collaborate with internal teams and external vendors to operationalize AI features as shared services
• Write clean, well‑tested, production‑ready code with strong engineering discipline
• Contribute to architectural decisions and help define team best practices
• Well versed with AI driven development tools – Cursor, Claude, Copilot, Replit, etc.

WHAT WE'RE LOOKING FOR

• 5–7 years of total engineering experience with demonstrable GenAI production deployments
• Strong Python expertise; experience with FastAPI, async patterns, and REST API design
• Hands‑on with LLM frameworks: LangGraph, LlamaIndex, LangChain, or equivalent
• Experience with multimodal AI — image/audio/video generation, ASR, TTS, or voice models
• Solid understanding of RAG architectures, vector stores, embeddings, and retrieval strategies
• Comfortable with cloud‑native deployments on GCP, Azure, Runpod
• Excellent communication and cross‑functional collaboration skills
• Ownership mindset — you take a feature from ideation to production

TECH STACK

Core (required):

Supporting:

NICE TO HAVE

• Experience with speech / ASR models (Whisper, Sarvam AI, Azure STT) or TTS / voice cloning (VC) pipelines
• Exposure to multilingual NLP for Indic or global‑south languages
• Prior work in EdTech, social impact, or mission‑driven organisations
• Published projects, open‑source contributions, or patents in AI/ML

EDUCATION

B.Tech / M.Tech / M.S. from a premier engineering institution — IITs, NITs, IIITs, or equivalent top‑tier colleges. We value the rigour and problem‑solving foundation that comes with this background. Exceptional candidates with non‑traditional paths but strong production AI experience will also be considered.

WHY THIS ROLE

• Work on AI systems with real, measurable impact — serving learners across India, Brazil, Mexico, Philippines and Indonesia
• Operate at the frontier of GenAI — RAG, agentic orchestration, multimodal pipelines — in a production environment
• Lean team with high ownership — your decisions shape the architecture, not just the code
• Mission‑driven organization backed by decades of grassroots work in skilling and education

Ready to build AI that actually matters?