Jitam Barman

Jitam Barman

A Bit About Me

I am a Dual Degree (BTech + MTech) student at IIT Kharagpur, specializing in Metallurgical and Materials Engineering with a minor in Computer Science and Engineering. My interests lie at the intersection of AI, machine learning, and Materials Engineering.

Beyond academics, I lead the sponsorship team of COMPOSIT, the annual departmental fest, and stay active in hall life, and literary events.

Education

IIT Kharagpur — BTech & MTech Dual Degree, Metallurgical & Materials Engineering 2023 – Present
Read my blog →
Resume Experience Skills Projects POR Activities

Experience

SNN-based Quadratic Programming

— University of Oulu, Finland
Apr 2026 - Present
  • Formulating a Chance-Constrained QP (CCQP) over the alloy composition simplex via a Gaussian Process surrogate for multi- property steel alloy design, achieving probabilistic yield-strength targeting <5% constraint violation rate on Matbench samples.
  • Proved a novel theoretical equivalence between Poisson spike-train noise in SNN solvers and Gaussian uncertainty propagation through quadratic objectives, enabling principled uncertainty quantification without additional Monte Carlo overhead.
  • Benchmarking the proposed SNN-CCQP framework against classical convex solvers (CVXPY/OSQP, SOCP) and state-of-the-art Bayesian optimisation (BoTorch) on the Matbench steels dataset, evaluating optimality gap, constraint satisfaction rate

Skills

Languages
Python C C++ JavaScript SQL HTML / CSS MATLAB
ML / AI
TensorFlow Scikit-learn Pandas NumPy SciPy Matplotlib NLP RAG
Web / App
React.js React Native Expo Streamlit Bootstrap
Tools & Platforms
Git / GitHub VS Code Jupyter Notebook Google Colab Kaggle Xcode Autodesk Fusion 360

Projects

Real-Time Financial RAG Bot

A real-time RAG engine for financial analysis — listens to live markets, processes news streams, and reads uploaded documents to provide instant, data-backed answers.

Pathway Streamlit SQLite LLM
View on GitHub

Backstory Consistency NLP

A RAG-based NLP pipeline that verifies character backstories against entire books to detect narrative inconsistencies, using Pathway for vector search and Groq LLMs.

NLP Pathway RAG Groq
View on GitHub

Explore KGP

A gamified campus exploration app with a "fog of war" mechanic — the map reveals itself only as you physically walk through the world. Built with React Native and Expo.

React Native Expo Geolocation
View on GitHub

2048 Number Rush

A fun, interactive recreation of the classic 2048 sliding puzzle game.

JavaScript
View on GitHub

Position of Responsibility

Head - Sponsorship

— COMPOSIT, IIT Kharagpur
Nov 2024 – Apr 2026
  • Managed and led the sponsorship team to secure |8Lakh+ in fund across 2025–26 cycles from 10+ corporate partners

Secretary

— Azad Hall of Residence
Oct 2024 – Apr 2025
  • Coordinated different General Championship events and performed in the Gold winning Illumination and Rangoli’24

Activities

Made with the assistance of Claude Opus