Ameya Kulkarni

     

currently: building in public, shipping real tools, two internships deep

• Building a Next.js AI Literacy Portal at TCET Centre of Excellence and internal automation tools in Python (May 2026)
• AI Systems Evaluation Intern at AirDawg Labs on Project Terminus-2nd-Edition by Snorkel AI, reviewing and submitting benchmark tasks used to train frontier models for OpenAI and Anthropic (Jun 2026)
• Maintaining Mustel, a Python CLI and MCP server with 4,400+ PyPI downloads
• Founded The Free University with 90,000+ lifetime visits and 1,000+ LinkedIn followers

Non-AI static analysis layer for AI coding agents (Cursor, Claude Code, Windsurf). Deterministic scanning, no model calls, no hallucinated findings.

• Orchestrates three engines (Ruff, Bandit, pip-audit) plus 20 custom YAML pattern files covering subprocess, requests, flask, django, pickle, asyncio, and more
• Normalizes everything into a schema-versioned JSON report, with a precomputed agent_prompt field so an AI agent can act on it without parsing the raw output
• Ships an MCP server (mustel serve) exposing review, review_file, env, and check_package tools for direct IDE and agent integration
• Benchmarked at 100% recall across 14 planted bugs in 4 test projects, 0 false positives on a clean baseline

mustel review        # scan current directory, outputs JSON
mustel serve          # run as an MCP server for AI IDEs

Stateless Monte Carlo simulation API for stock price paths, built on Geometric Brownian Motion (GBM).

• FastAPI backend, fully stateless, no auth keys required, single POST /v1/simulate endpoint
• Vectorized NumPy computation returns 1,000 simulated paths in milliseconds
• Returns p10/p50/p90 percentile price envelopes along with annualized volatility and probability-of-profit
• Rate limited at both the Nginx layer (20 r/s, burst 30) and the app layer (100 requests per 5s per IP)
• Full stack runs via Docker Compose: FastAPI backend, Next.js frontend, Nginx reverse proxy

Rolling window statistics for NumPy arrays, without pulling in pandas.

• mean, std, sum, min, max, zscore, normalize, apply, all under one consistent function signature
• Uses numpy.lib.stride_tricks.as_strided for zero-copy windowing, and locks the returned views read-only to avoid segfault-prone manual stride math
• Supports min_periods to mask incomplete windows instead of failing on them
• 700+ monthly PyPI downloads, CI on every push via GitHub Actions

Flask app for image compression, resizing, and image-to-PDF merging, all done in memory.

• BytesIO-based processing, no files touch disk beyond the request lifecycle
• Resize by percentage, adjustable JPEG/PNG compression quality
• Merges multiple uploaded images into a single PDF
• Files auto-delete 5 seconds after generation, no logging, no stored metadata

A free course and certification aggregator I founded and grew from scratch. It manually vets free courses and certifications from providers like Google, Harvard, IBM, Cisco, and freeCodeCamp, and runs interactive in-browser learning spaces (including a Python zero-to-production track with live code execution) plus instant Python and web compilers, so people can learn without wading through paywalled content.

• 90,000+ lifetime visits, 1,000+ LinkedIn followers
• 117+ certifications listed, all manually reviewed
• Built and SEO-optimized from scratch, zero paid promotion

AI Systems Evaluation Intern · AirDawg Labs  Jun 2026 – Present

Working on Project Terminus-2nd-Edition by Snorkel AI. Reviews AI coding agent benchmark tasks for instruction clarity, test alignment, rubric quality, metadata correctness, Docker/base image compliance, and solution leakage risks. Evaluates full task submissions by inspecting task environments, verifier reports, Dockerfiles, task.toml, and oracle solutions before making Accept / Needs Revision decisions. Also contributed as a task submitter before moving to the reviewer side. Ubuntu / WSL, Docker, Python.

Software Intern · TCET Centre of Excellence  May 2026 – Present

Contributing to a Next.js web portal for AI literacy training. Building Python-based internal automation tools.

Research Analyst → Associate Data Analyst · CoreLayer Labs (Review.AI)  Oct 2024 – Feb 2025

Built an LLM-powered product-page scraper cutting manual review time by 75%. Built a real-time Streamlit dashboard integrated with Google Sheets for team workload tracking. Researched and documented 50+ AI tools.

• Problem Setter · Shastra Coding Club, TCET. Designs and validates test cases for T&P coding assessments
• Mumbai Hacks 2025. Built LifeLink (AI organ donation platform), qualified for Round 2 offline of India's largest agentic AI hackathon (HealthTech track)
• CGPA 9.21 / 10 · B.E. Information Technology, Mumbai University

Mumbai · open to opportunities