tanay@github:~$ whoami
> Tanay Shah
tanay@github:~$ cat /etc/profile
> Founding AI Engineer · New York City
> CS @ UMD '25 · Departmental Honors · Statistics minor
> I build things that shouldn't work, but do.
> Currently: production agent infrastructure, sandboxed
> Python runtimes, MCP servers, iOS apps from zero.
tanay@github:~$ whereis tanay
> New York, NY
tanay@github:~$ curl -s tanayshah.dev/links
> https://tanayshah.dev
> https://tanayshah.dev/hire
> https://linkedin.com/in/tanayshah11
> https://github.com/tanayshah11
> tanayshah2024@gmail.comTanay Shah is a Founding AI Engineer in New York City, available for hire as of May 2026. Most recently: 14 weeks of founding-engineer reps at a Y Combinator F25 AI startup — production agent infrastructure (LangGraph + Anthropic Claude), a hardened Python sandbox (bubblewrap + seccomp + AST validation) for Zero-Data-Retention compliance, durable event-sourced chat backends, iOS apps shipped from zero. Open to founding, first-engineer, and early-stage AI roles.
→ Email: tanayshah2024@gmail.com
→ Portfolio: tanayshah.dev
→ Hire page: tanayshah.dev/hire
→ Resume: Tanay_Shah_Resume.pdf
→ LinkedIn: linkedin.com/in/tanayshah11
AI engineer in NYC · founding-engineer reps · agent infrastructure · sandboxed runtimes · MCP · iOS · ZDR-grade
📝 What the Bubblewrap Sandbox Escape Tells Us About Agent Runtime Hardening in 2026
📝 Picking MCP Servers for an Agent — A Selection Heuristic for 2026
📝 Designing Tool Surfaces for LLM Agents
📝 Multi-Vendor Agent Design — Why One Model Isn't Enough in 2026
📝 Building a Zero-Data-Retention Layer for Production LLM Agents
