Pushkar's
PORTFOLIO

Quantitative & Machine Learning Researcher | MSc AI @ Imperial College | B.Tech @ IIT Guwahati

Quantitative & Machine Learning Researcher | MSc AI @ Imperial College | B.Tech @ IITG

Quantitative & Machine Learning Researcher |
MSc AI @ Imperial College | B.Tech @ IIT Guwahati

View Research & Projects

Curriculum Vitae

THINK DIFFerent

[ About me

I am a Quantitative and AI Researcher pursuing an MSc in Artificial Intelligence at Imperial College London, with an engineering foundation from IIT Guwahati. My work bridges rigorous statistical modeling, algorithmic optimization, and applied deep learning to solve complex quantitative problems.

Across research appointments at UPenn and the MIT Media Lab, I have developed novel segmentation architectures, engineered differentiable calibration methods for complex systems, and designed statistical hypothesis frameworks. My technical foundation centers on Python, PyTorch, C/C++, and low-latency system optimization.

See My Work

See My Work

Co-first author – Submitted to AI in Neuroscience journal

PIGMENT: A deep learning framework for Porcine Immunohistochemistry seGMENTation
Pushkar Ambastha, Javid Dadashkarimi, Sai Krishna C. Annavazala, Drew Parker, Ramon Diaz-Arrastia, Hailong Song, Rebecca P Donahue, Douglas H. Smith, Jean-Pierre Dollé, Victoria E. Johnson, John A. Wolf, Ragini Verma

PIGMENT: A deep learning framework for Porcine Immunohistochemistry seGMENTation
Pushkar Ambastha, Javid Dadashkarimi, Sai Krishna C. Annavazala, Drew Parker, Ramon Diaz-Arrastia, Hailong Song, Rebecca P Donahue, Douglas H. Smith, Jean-Pierre Dollé, Victoria E. Johnson, John A. Wolf, Ragini Verma

LINK

LINK

Submitted to ACM Computing Surveys

Pushkar Ambastha, From AlphaFold 2 to AlphaFold 3: Architecture & Generalization Review
Under review at ACM Computing Surveys (IF: 23.8)

Investigated recent advances in protein structure prediction, like AlphaFold 3, which depicted a pattern toward the generalization ability of the models leading toward Large Language Models (LLMs).

Pushkar Ambastha, From AlphaFold 2 to AlphaFold 3: Architecture & Generalization Review
Under review at ACM Computing Surveys (IF: 23.8)

Investigated recent advances in protein structure prediction, like AlphaFold 3, which depicted a pattern toward the generalization ability of the models leading toward Large Language Models (LLMs).

LINK

LINK

Featured Works

Research

FEATURED

Synthetic Human Memories

WHERE

MIT Media Lab

YEAR

2024-25

FEATURED

Synthetic Human Memories

WHERE

MIT Media Lab

YEAR

2024-25

FEATURED

Synthetic Human Memories

WHERE

MIT Media Lab

YEAR

2024-25

FEATURED

PIGMENT

WHERE

Univ. of Pennsylvania

YEAR

2024-26

FEATURED

PIGMENT

WHERE

Univ. of Pennsylvania

YEAR

2024-26

FEATURED

PIGMENT

WHERE

Univ. of Pennsylvania

YEAR

2024-26

FEATURED

Immunological ABM

WHERE

MIT Media Lab

YEAR

2023-25

FEATURED

Immunological ABM

WHERE

MIT Media Lab

YEAR

2023-25

FEATURED

Immunological ABM

WHERE

MIT Media Lab

YEAR

2023-25

See all the other works ↗

See all the other works

What I Work

Projects

Domain-specific Question Answering chatbot (Inter-IIT Gold)

We develop pipelines to retrieve a knowledge base article from the database based on the query and answer the query using the retrieved passage. We optimize the pipeline for performance, latency, and resource usage. Developed a low-latency QA retrieval system using DeBERTaV3. Applied model distillation, sparsification, and quantization to reduce inference latency by 39.82% (<1000 ms) while achieving an 83.77 F1 score.

We develop pipelines to retrieve a knowledge base article from the database based on the query and answer the query using the retrieved passage. We optimize the pipeline for performance, latency, and resource usage. Developed a low-latency QA retrieval system using DeBERTaV3. Applied model distillation, sparsification, and quantization to reduce inference latency by 39.82% (<1000 ms) while achieving an 83.77 F1 score.

GitHub Repo
Technical Report

Options Pricing and Market Calibration Simulator

Built a Black-Scholes pricing engine simulating call/put P&L and Greeks across 100+ spot-volatility scenarios. Visualized pricing discrepancies and sensitivity regimes across a 10×10 volatility–spot surface to evaluate mispricings under dynamic volatility environments.

Built a Black-Scholes options pricing simulator with Streamlit and yfinance, and modeled call or put Profit and Loss across 100+ spot-volatility grid scenarios. Generated 4 interactive heatmaps over a 10×10 volatility–spot grid to visualize PnL and pricing errors under shifting volatility regimes.

Built a Black-Scholes pricing engine simulating call/put P&L and Greeks across 100+ spot-volatility scenarios. Visualized pricing discrepancies and sensitivity regimes across a 10×10 volatility–spot surface to evaluate mispricings under dynamic volatility environments.

GitHub Repo
Live App

BioNLP & Genomic Sequence Modeling

Fine-tuned DNABERT for functional genomics sequence classification (+5% F1) and built a SARS-CoV-2 classifier achieving 99% accuracy. Automated active site analysis workflows for 10,000+ protein structures.

Fine-tuned DNABERT for functional genomics sequence classification (+5% F1) and built a SARS-CoV-2 classifier achieving 99% accuracy. Automated active site analysis workflows for 10,000+ protein structures.

GitHub Repo - P1
GitHub Repo - P2

Multi-Modal Generative AI Pipeline

Cover Generation using OpenAI tools

Built an end-to-end multi-modal pipeline converting audio signals to contextual imagery using Whisper, fine-tuned GPT-2, and Latent Diffusion Models (CLIP score: 0.325).


Developed a multi-modal pipeline that converts audio/text input into images using state-of-the-art OpenAI tools. Generated optimal transcripts for the podcasts and songs with OpenAI Whisper to use in creating prompts.

GitHub Repo
Hugging Face Space

Path

Four institutions, one throughline: rigorous problem-solving at the intersection of ML and research.

01

IITG

01

IITG

B.Tech in BioEngineering | Strong Quantitative & Engineering Core

02

MIT

02

MIT

Two labs, two years, built differentiable ABMs and ran statistical studies on AI-driven false memory formation.

03

UPenn

03

UPenn

Co-first author on a segmentation framework outperforming SOTA baselines by up to 95% detection rate.

04

Imperial

04

Imperial

Starting MSc AI Applications on a competitive scholarship — solving quantitative and machine learning problems

01

B.Tech in BioEngineering | Strong Quantitative & Engineering Core

IITG

02

Two labs, two years, built differentiable ABMs and ran statistical studies on AI-driven false memory formation.

MIT

03

Co-first author on a segmentation framework outperforming SOTA baselines by up to 95% detection rate.

UPenn

04

Starting MSc AI Applications on a competitive scholarship — solving quantitative and machine learning problems

Imperial

01

IITG

01

IITG

B.Tech in BioEngineering | Strong Quantitative & Engineering Core

02

MIT

02

MIT

Two labs, two years, built differentiable ABMs and ran statistical studies on AI-driven false memory formation.

03

UPenn

03

UPenn

Co-first author on a segmentation framework outperforming SOTA baselines by up to 95% detection rate.

04

Imperial

04

Imperial

Starting MSc AI Applications on a competitive scholarship — solving quantitative and machine learning problems

AWARDS

2026 Imperial India Future Leaders Scholar (£10K Award)

Kaggle 4X EXPERT - 2023

2023 Inter IIT Tech Meet Gold Medallist (DevRev.ai PS)

Bronze Medal (85th/1100), Kaggle - 2023 (Top 8%)

Bronze Medal (85th/1100), Kaggle, 2023

Bronze Medal (99th/1025), Kaggle - 2023

Bronze Medal (99th/1025), Kaggle, 2023

Convolve Hackathon (28th/231) - 2022

EXPLORE
MY SOCIAls

GITHUB

  • GITHUB

GITHUB

LINKEDIN

  • LINKEDIN

LINKEDIN

X.COM

  • X.COM

X.COM

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

  • SAY HELLO!

Let’s work together!

[ Marked fields are required to fill ]

Let’s work together!

[ Marked fields are required to fill ]

Let’s work together!

[ Marked fields are required to fill ]

Create a free website with Framer, the website builder loved by startups, designers and agencies.