Loading the site. Press Escape to skip the intro.

Software & Applied AI

Manankumar Thakkar

Software Engineer · AI Engineer · Applied AI

I build backend systems at Walmart Global Tech and applied-AI tools you can inspect.

See what I’ve built Résumé
Currently building atWalmart Global Tech
Meet Manan

About

Production systems. Measured AI.

Here’s my story.

I’m a Software Engineer III at Walmart Global Tech, building backend services for in-store advertising. I work on API performance, multi-tenant data design and AI tooling. Outside work, I build public AI projects and share the code, results and open questions.

Proof · Distributed systems

Fixed an N+1 API bottleneck with concurrent caching at Walmart: 60% lower latency and 10,000+ fewer DB calls/day (per resume).

Resume · Walmart performance work

SELF-ASSESSED DEPTH · SOURCES LINKED

Experience · 03

Where I've owned systems.

A few career moves…

  1. Walmart Global Tech

    Software Engineer III

    Previously Software Engineer · Jul 2024-Jan 2025

    Feb 2025 - Present

    • Cut API latency 60% and 10,000+ DB calls/day by fixing an N+1 bottleneck with concurrent caching.
    • Prevented a 6× data-key collision during international expansion with a country-scoped key.
    • Reduced production vulnerabilities 35% through Snyk fixes, credential cleanup and secret rotation.

  2. George Mason University

    AI Research Assistant

    Jul 2023 - Jul 2024

    • Built LLM research tooling to streamline manual workflows.
    • Provisioned reproducible research environments with Terraform.

  3. Nokia

    Test Automation Engineer (co-op)

    Sep 2022 - Jun 2023

    • Python automation cut manual testing effort 50%.
    • Jenkins test integration cut defect density 20%.

  4. Let It Wag

    Full Stack Developer

    Jun 2019 - May 2020

    • Node.js APIs: 13K+ users, 20% efficiency gain.
    • Built a responsive React UI supporting 100+ user journeys.

M.S. Computer Science · George Mason University · 2023

Selected work · 04

Public code, lessons learned.

Some things I've built…

Public infrastructure

MCP Observatory

MCP Security Observatory live site, showing its scan and disclosure summaries.
Live site · 5 Oct 2026
Problem
MCP plugins can access files and shell. Review should not require running them.
I built
Static analysis, reproducible sampling, gated disclosure and a nightly public index. Sole author.
Outcome
1,673 scanned · 171 findings published
  1. Sample
  2. Inspect source
  3. Gate publication

2026-10-04 snapshot. Accuracy is unmeasured; findings are not confirmed vulnerabilities.

  • Python 3.11+
  • tree-sitter
  • SARIF / JSONL
  • pytest · ruff · mypy
  • GitHub Actions / Pages
Case study : MCP ObservatoryLive : MCP Observatory (opens a new tab)GitHub : MCP Observatory (opens a new tab)

Applied AI experiment

The Escalation Gate

The same answerability gate scored 100% with random negatives and 69.5% with hard negatives.
Same model · same prompt
Problem
RAG pipelines pay for generation even when retrieval cannot answer the question.
I built
A three-group answerability evaluation, calibration analysis and billing audit. Sole author.
Outcome
100% → 69.5% with hard negatives
  1. Question + passage
  2. Typed decision
  3. Route the judgment

600 SQuAD-derived decisions · ~$0.13. Floor per author audit; enterprise transfer untested.

  • Python 3.11+
  • Jev (TypeSafe AI)
  • SQuAD 2.0
  • LLM evaluation / calibration
Case study : The Escalation GateGitHub : The Escalation Gate (opens a new tab)

Contact · 05

Let's build
what's next.

Software Engineer · AI Engineer · Applied AI

Let's connect

Start a conversation

mananaiya@gmail.com

LinkedInGitHubRésumé

Manankumar ThakkarUnited States