Skip to content
View parthtiwari-dev's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report parthtiwari-dev

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
parthtiwari-dev/README.md

Note

I build AI systems that know when they're wrong. Most LLM features ship with no measurement, which means they can't be wrong — they can only be vibes. I build the harness that catches the lie first, then the system around it.


Selected work

BeatMind — AI music generation and dissection

beatmind.tech · live, real users · private repo, walkthrough on request

Upload a track; get back an editable arrangement. Separated stems, detected song structure, per-section fragments you can regenerate, repaint and mix down. Built and operated solo.

Scale ~95,000 lines · a Next.js app on Vercel and four Python workers on Modal
Audio ML BS-RoFormer vocals · htdemucs_ft drums and bass · all-in-one-fix structure · essentia key · madmom chords
The hard part a fenced, webhook-driven job state machine — dispatch attempt tokens, a reconciler cron, idempotent at-least-once callbacks, because GPU containers are cold, slow and allowed to fail
A decision I measured benchmarked L40S vs A100 vs H100 on a pinned seed and declined the upgrade — L40S was cheaper and faster, because diffusion turned out to be 0.42s of a 16.3s pipeline

QueryPilot — self-correcting text-to-SQL agent

Live API · LangGraph FastAPI ChromaDB PostgreSQL

Language → schema-aware retrieval → SQL → static validation → a three-stage self-correction loop before anything touches a database.

Measured on Result
82-query e-commerce benchmark, first attempt 90.0% executed correctly
the same 82 queries, after self-correction 95.7%
tables or columns invented across that run none
a separate library schema, zero domain tuning generalised

UPI Fraud Engine — real-time fraud decisioning

Live API · Live UI · XGBoost FastAPI DuckDB Great Expectations

Built under the constraints a real fraud desk has, not the ones a notebook has: score at time T using only pre-T features, live inside a 0.5% daily alert budget, and survive labels that arrive late.

Measured under Result
a 0.5% daily alert budget 92.06% precision
the API scoring path ~386ms at p95
temporal integrity 55+ leakage tests
replay day-by-day backtest

Evidence-Bound Drug RAG — medical retrieval that refuses

Live app · HuggingFace Space · ChromaDB LangChain RAGAS

FDA and NICE source documents, in a domain where a hallucination is patient harm. Every claim carries its citation, and insufficient evidence triggers a refusal instead of a guess.

Measured on Result
RAGAS faithfulness over answered questions ~0.99
questions with no supporting evidence refused, not guessed
the full evaluation run $0.168
scope non-diagnostic — not medical advice

A signal trace catching an anomaly

Three things that broke

The work I am proudest of is the bugs I found in my own systems before anyone else did — and I found them because the harness existed first.


A fraud model that was lying to itself.

train ROC-AUC      0.895     looked ready to ship
production ROC     0.60      it had been reading the future the whole time

Temporal features had bled post-event signal into pre-event training windows. Fixed with point-in-time enforcement and 55+ leakage tests, then rebuilt from scratch. Precision held under a real alert budget, which is the only number that ever mattered.

Why a backtest is not a train/test split

A random split asks can this model separate these rows. A fraud desk asks would this model have caught it on the day, knowing only what was knowable then. Those are different questions, and only one of them predicts production.

The 0.5% alert budget is the part people skip. A fraud model with 99% recall is worthless if it flags 8% of traffic, because no human team can review that. Precision inside a fixed budget is the real constraint — so it became the metric the model was selected on, rather than a number reported afterwards.


A hallucination rate of 100% that was a bug in the metric, not the system.

schema_tables_used was returning ["schema_dict", "tables"] — the keys of a dict, not the table names inside it. Every comparison against the real schema failed, so every query looked like a hallucination. The true rate was 0%. One-line fix.

I only found it because I had written a hallucination detector at all. The sharper lesson is underneath: your evaluation code is code, and it has bugs. An eval harness nobody has questioned is just a second thing that can lie to you, with more authority.


An LLM answering a revenue question with SELECT SUM(amount) FROM fines.

Two database schemas were sharing one Chroma collection and the embeddings leaked across them, so a question about an e-commerce table retrieved context from a library one. Fixed with prompt isolation and schema-scoped retrieval, then the entire 82-query benchmark was re-run rather than spot-checked — because a fix you only test on the failing case is a guess.


How I build

flowchart LR
    A["define what<br/>'working' means"] --> B["build the<br/>eval harness"]
    B --> C["write the<br/>system"]
    C --> D["break it<br/>on purpose"]
    D --> E{"does it<br/>hold?"}
    E -->|no| F["fix"]
    F --> D
    E -->|yes| G["ship with<br/>monitoring"]
    G -.->|"production proves<br/>you wrong"| A
Loading

The dotted line is the important one. Everything above it is discipline; that one is humility, and it is the only reason the discipline is worth anything.


Stack

Core — Python · FastAPI · PostgreSQL · Docker AI/ML — LangGraph · LangChain · RAG · ChromaDB · RAGAS · XGBoost · PyTorch audio models Infrastructure — Modal (GPU) · Vercel · Render · Neon · Cloudflare R2 · GitHub Actions Frontend — TypeScript · Next.js · Vue · Three.js

Currently

AI/ML intern at Stick and Dot, building Vivid — creative AI tooling, in beta with real users.

Operating BeatMind in production, where the bug reports come from working musicians and are consistently more interesting than anything I would have thought to test.




Working together

Currently taking on 1–2 freelance projects, and open to full-time roles.

What you get Timeline From
Reliability audit I take your RAG or agent, build a real evaluation set against it, and hand you a report: where it fails, how often, and what each fix is worth. 1 week $500
Eval harness + fixes The harness above, wired into CI, plus the failures it surfaces actually fixed. 2–4 weeks $1,500
Retainer Ongoing evaluation, regression monitoring and iteration as your system and your data drift. monthly $1,000/mo

Bring me a chatbot that invents things · a text-to-SQL feature you cannot trust with a real schema · a model that looked good in the notebook and died in production · an LLM pipeline nobody has ever measured.

parthti2003@gmail.com — tell me what is failing and I will tell you, free, whether I think I can fix it.


Bengaluru, India · remote · portfolio · linkedin

Pinned Loading

  1. parth-tiwari parth-tiwari Public

    my portfolio

    Vue

  2. querypilot querypilot Public

    QueryPilot -Production-ready multi‑agent Text-to-SQL API for Postgres. Schema‑aware LangGraph pipeline with ChromaDB + sentence‑transformers, Neon-backed DB, and full evaluation on real ecommerce &…

    Python 3 1

  3. Evidence-Bound-Drug-RAG Evidence-Bound-Drug-RAG Public

    Evidence-grounded medical RAG system that retrieves FDA and NICE drug guidelines, generates cited answers, and safely refuses unsupported queries to minimize hallucinations.

    Python 1

  4. oncoverse oncoverse Public

    OncoVerse is an open-source cancer education atlas that makes cancer biology visible through immersive 3D anatomy, plain-English explanations, and stage-by-stage exploration for patients, families,…

    TypeScript

  5. tathya tathya Public

    Tathya (तथ्य, 'fact') ~ an autonomous, non-partisan record of India's central government. No manual topic selection, no AI verdicts: public sources are watched continuously and clustered into sourc…

    Python 1

  6. upi-fraud-engine upi-fraud-engine Public

    Real-time UPI fraud detection system (0.8953 ROC-AUC) with <500ms FastAPI scoring, 480+ temporal features, and budget-aware alerts under fintech constraints

    HTML 3