What I'm
doing now.
The /now page convention — what's actually current, updated regularly. Last revised 2026-05-10.
Open to founding-engineer roles in NYC. Most recently: Founding Engineer at Structured AI (NYC). 14-week tenure, 1,035 commits, agent infrastructure + ZDR-compliant Python sandbox + iOS app from zero. Now in market for the next founding-engineer role at an applied-AI startup or infra/platform team.
Founders, hiring engineers, and recruiters at applied-AI startups. Particularly excited about teams working on agent infrastructure, MCP, multi-vendor LLM orchestration, AI safety / sandboxing, durable chat, real-time data, and vertical AI for regulated domains.
If you're building any of those — please email tanayshah2024@gmail.com. I respond within 24 hours.
Public case studies of agent infrastructure work. Each entry shows the why, the architecture, and the lessons. The most recent additions:
- → Real-Time Sales-Conversation Coaching Agent — two-path architecture (sub-2s live coach + post-call deep dive)
- → Travel MCP Server — flights, hotels, weather as MCP tools with per-tool TTL caching
- → Mercury Stream — real-time market data pipeline with on-anomaly black-box flight recorder
- → AI Agent Error-Handling Patterns — 4 production reliability patterns on Trigger.dev v4
Field-report blog posts on agent infrastructure. Each is shaped for engineering depth, not vendor marketing. All published May 9 2026 — fresh.
- 📝 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
Anthropic Claude Opus 4.7 (GA April 16 2026 — 1M context, 128K max output, adaptive thinking, 2576px image support) and the implications for long-context agent design. The April 2026 Claude Code Bubblewrap escape (documented by Ona) and the May 2026 Microsoft Semantic Kernel CVEs (CVE-2026-25592, CVE-2026-26030) plus the Claude Code Hooks CVE-2026-21852 — agent runtime hardening as a security discipline of its own. Production agent eval methodology; Apache AGE for graph memory; how vertical-AI startups structure training pipelines.
- → AI Week New York — May 11-17 2026 (right now)
- → Agentic AI Summit — June 4 2026, NYC
- → Knowledge Graph Conference — Cornell Tech NYC + online
- → AI Engineer NY — October 12-14 2026, NYC (the year-end one)
New York City. Open to relocation for the right team. Will travel for the right team. Time zone: ET.
Python 3.12 (asyncio TaskGroup) · TypeScript 5.5+ · Swift / SwiftUI · Anthropic Claude (Opus / Sonnet) · Google Gemini 3 Pro Vision · Llama 3.3 70B (via Groq) · LangGraph · Anthropic Claude Code SDK · Trigger.dev v4 · Model Context Protocol · FastAPI · PostgreSQL (asyncpg, pgvector) · Redis · gRPC + Protobuf · bubblewrap + seccomp · Apache AGE · Docker multi-stage · Vercel · Azure Container Apps Jobs.