Staff AI Engineer · Platform AI

Multi-agent systems built for real users, not demo day.

When production agents fail, I fix them in your repo: orchestration, fine-tuning, tool use, retrieval, and eval gates you can trust. I have shipped multi-agent products at staff level and co-founded a voice-AI startup. I also research multi-agent RL part-time at the University of Groningen.

Start with a diagnostic Message on LinkedIn Case studies

4h US overlap · 6:30–9:30 PM IST (8:00–11:30 AM ET)

8-figure

Product ARR unblocked with agentic browser automation

~50%

Faster ship cycles after trace-backed eval gates in CI

2 days → min

Agent routing across structured + unstructured data

Start here

Two ways to start. Clear deliverables. Terms agreed on LinkedIn.

Agent system diagnostic

5 business days

We map how your agents behave in production: tools, handoffs, retrieval, and eval coverage. You get a clear picture before committing to a build phase.

Eval scorecard on agent workflows (tools, retrieval, generation, multi-step paths)
Failure taxonomy: top regressions ranked by user impact
Fix recommendations with effort estimates
30-min readout with your eng lead

Scope and commercial terms agreed on LinkedIn.

2-week productionization pilot

2 weeks

Hands-on work in your repo, not a slide audit. Week 1 establishes a baseline; week 2 lands fixes and eval integration.

Week 1: failure taxonomy + eval baseline merged in your repo
Week 2: quality gate + 2 critical-path fixes on prod agent or retrieval flows
Handoff runbook your team extends

Often follows the diagnostic when there is a fit. Terms scoped on LinkedIn.

Full service list →

How I work

Typical engagement: 3–6 months
4h US Eastern overlap daily, held as a fixed calendar block
Week 1 includes PRs in your repo (with prod access you scope). First milestone is shipped work, not decks.
Availability and scheduling constraints confirmed in writing before kickoff.

What I do