Hi 👋, I'm Apoorva Verma

_{All highly competitive, national-level selections.}

JPMorgan Chase — Quantitative Research Mentee — 1 of 35 students across India
McKinsey & Company — NextGen Women Leaders — top 50 women in India
Microsoft — Engage Mentee (2022)
D. E. Shaw — DESIS Ascend Educare Fellow — 1 of 35 selected from 6,200+ applicants across India

65 merged PRs across 29 external projects — zed, duckdb, posthog, directus, keycloak, weaviate, PapaParse, agents, sqlfluff, falcon, and more
33 accepted answers in GitHub Discussions across 23 repos — typer, turso, helix, dagster, litellm, bevy, spaCy, dbt-core, clap, textual, and more

AI reliability & evaluation — my core focus: making LLM systems dependable, not just demos.

langchain-shannonbase — Python · LangChain · MySQL A LangChain VectorStore for MySQL 9's native VECTOR type — RAG on ShannonBase, self-hosted MySQL, or HeatWave, no separate vector DB. Fills a real ecosystem gap.
atlasai-mcp-bridge — TypeScript · Atlassian Forge An MCP bridge that brings Jira, Confluence & JSM into Claude, Cursor, and any MCP client — OAuth 2.1, Forge SQL, audit logging, React admin UI.
rag-eval-harness — Python RAG over research papers with a reproducible retrieval-evaluation harness (DeepEval + a custom citation-faithfulness metric).
claude-code-toolkit — Shell Skills, subagents, and hooks that make Claude Code follow good engineering practices by default.
dra-industry-4.0-assessment-platform — Next.js · PostgreSQL A digital-readiness platform that scores an organization's Industry 4.0 maturity and surfaces actionable insights.

Published ML research — "Crime Detection System using Face Recognition", Indian Journal of Applied Research (2022) — 88%+ accuracy, sub-4s inference
Oracle Cloud Infrastructure 2024 Certified Foundations Associate

Languages

AI / ML

Backend & Frontend

Data & Infra

Building and evaluating AI systems that actually ship — and growing women's representation in STEM along the way.