Location: Pune, India (In-office / Hybrid)

Reporting to: Director of Engineering

Company Stage: Early-stage (0→1)

About the Company

We are a tech startup helping e-commerce brands win AI visibility—making their data answer-ready so AI engines like ChatGPT, Gemini, Perplexity, and others can understand, trust, and cite them.

Our early focus is Shopify merchants in the $5–50Mn revenue range. We’re building in a rapid-moving, founder-led setting where speed, ownership, and learning matter more.

The role - Glu AI FDE In this role, you’ll build production‑ready AI systems designed for real‑world performance and reliability. You’ll architect and deploy LLM endpoints with strong guardrails and structured outputs, implement RAG pipelines that can be measured, defended, and presented to clients, and design agentic systems from first principles. Your work will span single‑agent loops to full multi‑agent orchestration using LangGraph, MCP,



and A2A, giving you hands‑on experience with AI systems that coordinate, reason, and execute at scale.

You’ll also build compound agent memory and deploy persistent, always‑on agents for real‑time applications. You’ll evaluate your systems using the TRACE framework, ensuring you can prove reliability, quantify performance, and communicate results with confidence. Candidates should have 4+ years of experience with Python or TypeScript/JavaScript and a proven history of shipping production‑grade AI components.

Prior experience developing LLM APIs, building defensible RAG systems, working with MCP and A2A frameworks, designing agent memory, and running structured evals in real products or client environments is essential.

📌 AI FDE (Forward Deployed Engineer) (Pune)
🏢 Glu
📍 Pune