Skip to content
View Partha-Shankar's full-sized avatar

Block or report Partha-Shankar

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
Partha-Shankar/README.md
Partha Shankar: Machine Learning Systems That Can Show Their Work. Styled like a paper's title page, with the title shaded as a token attribution map.

portfolio  ·  linkedin  ·  leetcode  ·  email

Abstract. I'm a final-year computer science student in Bengaluru and an AI/ML engineer intern at Tapplent, where I work on enterprise RAG. Most of what I build ends up in front of someone who can overrule it: a radiologist, a pharmacist, a network operator, an HR admin. So I spend as much time on the evidence behind an answer as on the answer. I also contribute upstream, with five pull requests merged into Next.js, Hugging Face Transformers, Cloudflare's Workers SDK and Apicurio Registry. I've also co-authored two research papers.

Keywords: open source, retrieval-augmented generation, explainable AI, computer vision, serverless systems.

1. Upstream

Five merged pull requests in four projects. They're small on purpose, and two got smaller in review: Cloudflare's maintainers had me drop a set of migration warnings, and Hugging Face had me delete my test. Both calls were right.

Timeline of five merged pull requests in 2026: cloudflare/workers-sdk #14394 on 23 June and #14530 on 6 July, vercel/next.js #95358 on 2 July, huggingface/transformers #47158 on 14 July, and Apicurio/apicurio-registry #8950 on 29 July. In total, 333 lines added and 11 removed, across projects with over 300k combined GitHub stars.

Each card below links to its pull request.

vercel/next.js #95358, merged. The cacheHandlers name check wasn't anchored, so invalid names passed. Added regression tests.

huggingface/transformers #47158, merged. A warning told people debugging multi-GPU inference the opposite of what the code does.

cloudflare/workers-sdk #14394, merged. Escapes the migrations table name and migration filenames in D1 SQLite queries.

cloudflare/workers-sdk #14530, merged. Adds type checks for four optional D1 binding fields that were being silently accepted.

Apicurio/apicurio-registry #8950, merged. Adds a wildcard path to the Not Found route so unknown URLs render the 404 page.

In review: pytorch/pytorch #188945, assert_close comparisons with Python and NumPy scalars.

2. Now

AI/ML Engineer Intern, Tapplent (Sep 2026 – present). I'm building a RAG chatbot over 1,000+ HR policy documents for Tapplent's HCM clients. Retrieval combines dense vectors with BM25 and re-ranks with a cross-encoder, which cut retrieval noise and hallucinations by over 40%. Answers cite their source documents, and metadata filters keep each user inside their access level.

Before this: Cloud & DevOps Trainee at Torii Minds (Aug 2025 – Jan 2026), working on AWS and GCP infrastructure and CI/CD.

3. Selected work

Two questions shape most of my design decisions. Can the person relying on this check it? And does it still work when conditions are bad?

3.1 Can you check it?

Project What it does How you can check it
DeepBreath AI Classifies chest X-rays as normal, bacterial or viral pneumonia with a five-model ViT ensemble (~94–96% accuracy), then estimates 3D consolidation volume from the single 2D image. Grad-CAM++ heatmaps are masked to segmented lung fields, so attention can't land on the heart or chest wall. Findings map to five named lobes.
CardioXAI Stratifies cardiovascular risk with a RF, XGBoost, LightGBM and TabPFN ensemble (cross-validated AUC up to 0.96 on UCI Cleveland), under 15 ms on CPU. A per-patient SHAP waterfall in under 10 ms, model disagreement reported as confidence, and a PDF report a clinician can keep.
MedLens AI Reads handwritten prescriptions with TrOCR, resolves drug names against RxNorm and flags interactions. Gemini runs only when extraction fails schema validation. Low-confidence results stop the pipeline. A review screen makes a person confirm the drug before anything downstream runs.
MFD-AI Detects manipulated images, video, audio and text in one consensus verdict. The verdict is built from separate forensic signals (ELA, PRNU sensor noise, FFT artefacts, optical flow, lip-sync), and all 35 analysis stages stream to the operator.

3.2 Does it hold up?

Project The conditions What happened
IKYA 2026 (live) A week of bursty registrations for an intercollegiate fest, with payments and jury scoring on the same platform. Ran on Cloudflare Workers, D1 and R2: 87,017 requests, 0 errors, 1.1 ms median CPU time, 2,500+ participants from 60+ colleges.
GramSetu AI Rural areas with unreliable internet, and photos people shouldn't have to upload. YOLOv8-nano and OCR run in the browser through ONNX Runtime Web and Tesseract.js, so images stay on the device.
HostelDesk Students sharing screenshots of their gate passes. QR codes are signed tokens that rotate every 60 seconds, across a seven-role outpass workflow.
RoadSoS Someone at a crash site, under stress, on a weak signal. One tap finds nearby hospitals and police. Results are cached for offline use, and it falls back when GPS or the map API fails.

4. Research

[1] Niranjan L, Mahalakshmi C K, Mahesh Kumar Jha, Vijay Anand P, Sajithra Varun, Partha Shankar. A Multi-Agent Reinforcement Learning Framework with Graph Neural Networks for Congestion-Aware Routing in Next-Generation Networks. 2026.
Combines CTDE multi-agent RL, a graph attention encoder and SHAP explanations for routing decisions. Against AI-CARF at full load: 36% lower latency (62 ms vs 97 ms) and 46% less packet loss. My part: the congestion index and reward function, the GAT encoder and the SHAP pipeline.

[2] Niranjan L, Ann Mathews, K. Ezhilarasan, Sajithra Varun, Mahalakshmi C K, Partha Shankar. A Deep Learning–Driven Intelligent Crop Prediction Model Integrating CNN–LSTM Architecture for Smart Agriculture. 2026.
A CNN–BiLSTM with temporal attention that recommends crops from soil, climate and satellite data, and names the factors behind each recommendation. My part: the multimodal data pipeline, SMOGN augmentation, the attention layer and hyperparameter tuning.

5. Stack

A matrix of tools against projects. Python, TypeScript, PyTorch, Hugging Face Transformers, OpenCV, scikit-learn, XGBoost, LightGBM, TabPFN, Gemini, Llama, ONNX Runtime Web, SHAP, Grad-CAM++, FastAPI, Flask, Cloudflare Workers, D1, R2, SQLite, React, Next.js, SvelteKit, Streamlit and Three.js, each marked against the projects that use it.

Also: C++, SQL, LangChain, LangGraph, MongoDB, AWS, Google Cloud.

6. Recognition

  • Winner, Vibexathon (national hackathon): team lead, MFD-AI
  • 2nd place, Nexora (national hackathon): team lead, MedLens AI
  • Round 3 qualifier, Flipkart GRiD 8.0, AI Engineering track
  • AWS Certified: AI Practitioner (AIF-C01), Solutions Architect Associate (SAA-C03)
  • B.E. Computer Science and Engineering, Nagarjuna College of Engineering and Technology, 2023–2027, CGPA 9.00/10

Correspondence: parthashankar21@gmail.com

Pinned Loading

  1. Pneumonia-detection-using-a-chest-xray Pneumonia-detection-using-a-chest-xray Public

    Research application for pneumonia detection on chest X-rays using a Vision Transformer ensemble, Grad-CAM++ heatmaps, and 3D lung reconstruction, built with Flask and React.

    Python

  2. MedLensAI MedLensAI Public

    Prescription Digitizer and Conflict Checker

    Python 1

  3. CBC_B-013 CBC_B-013 Public

    MindBridge: academic mental health platform with self-assessment screening, doctor booking, mood journaling, and an AI chat assistant, built with React, Express, MongoDB, and Flask.

    JavaScript

  4. huggingface/transformers huggingface/transformers Public

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

    Python 169k 35.3k

  5. cloudflare/workers-sdk cloudflare/workers-sdk Public

    ⛅️ Home to Wrangler, the CLI for Cloudflare Workers®

    TypeScript 4.7k 1.7k

  6. vercel/next.js vercel/next.js Public

    The React Framework

    JavaScript 144k 32.8k