About Forge & Function

Forge & Function is a founder-led AI engineering studio. We design and build production systems — the kind that run every day, under real load, with real money and real operations depending on them.

Most AI work stops at the demo. A notebook that impresses in a meeting, then quietly never ships. We started Forge & Function because the hard part isn't making something work once — it's making it work reliably, for years, in the messy conditions of a real business.

That conviction comes from the infrastructure side of the house. Before building AI platforms, we spent years keeping mission-critical enterprise databases alive — where a failed backup or an unhandled failover isn't a bug report, it's an outage. You learn to design for the day things break, not the day they demo.

So we build both halves. The intelligence — multi-agent orchestration, retrieval, grounding models in real data so they stop making things up. And the foundation beneath it — pipelines, databases, deployment, monitoring. One team, one accountable line from architecture to production.

How we approach the work

• Ship it or it doesn't count — A system that isn't in production isn't finished. Every engagement ends with deployed, documented, handed-over software — not a prototype and a slide deck.
• Grounded, not guessed — AI output is only as trustworthy as the data behind it. We serve facts from real sources and keep the model's job narrow, so answers hold up to scrutiny.
• Design for the bad day — Backups, failover, rate limits, edge cases. We plan for the failure modes up front, because that's what separates a system from a script.
• Direct, not layered — You talk to the engineer designing your system. No account managers, no telephone game, no context lost between the brief and the build.

Shubham Mandal

Founder & Principal Engineer

Shubham is an AI engineer and infrastructure architect who came to AI the long way around — through the unglamorous discipline of keeping enterprise systems running.

As a Senior Infrastructure Analyst at DXC Technology, he has spent 3+ years administering mission-critical Oracle environments on Unix/Linux: RMAN and Veritas backups at ~99.9% success, performance tuning through AWR and ASH, Data Guard failover drills, and automation that cut manual DBA workload by roughly 60%.

That foundation shapes everything the studio builds. Across 13+ delivered systems — LangGraph multi-agent platforms, RAG assistants, real-time trading engines, booking marketplaces and logistics optimizers — the constant is architecture that survives contact with production.

Focus areas: Multi-agent AI & RAG, Full-stack platforms, Data & cloud infrastructure, Algorithmic trading systems