Skip to content
View tejas-ml's full-sized avatar
🖥️
Working on a new project
🖥️
Working on a new project

Block or report tejas-ml

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
tejas-ml/README.md

Tejas Mahajan

PhD Student in Computer Science @ University of Central Florida (Computational Biology Lab)
Quantitative Researcher · AI/ML Scientist · High-Performance Software Engineer
Orlando, FL

Website Resume PDF Google Scholar LinkedIn LeetCode CodeChef Email


About Me

I am a PhD researcher in Computer Science at the University of Central Florida (Computational Biology Lab), working at the intersection of computational research and software engineering.

My work spans single-cell multi-omics & computational biology, quantitative finance, AI privacy & security, and high-performance software systems:

  • Single-Cell Multi-Omics & Computational Biology: Developing delay-aware, enhancer-gated Neural ODEs for gene regulatory network inference (ChronoGRN, Causal Dynamic GRN), single-cell foundation model embedding transfer, and multi-omics cancer patient stratification.
  • Quantitative Finance & Market Microstructure: Building low-latency orderbook/arbitrage simulators (Orderbook), analytical Black–Scholes options engines (TradeSim), event prediction markets (Tejas Trading), and the Rust → Quant interactive curriculum.
  • AI Security, Privacy & Architecture: Auditing synthetic data leakage (SyntheticShield), safeguarding RAG/LLM pipelines (RAGGuard, PromptLeakDetector, ModelCardSec), and designing QoS-aware CPU–AI DRAM schedulers (FairDRAM).

Featured Research & Projects

Category Project Highlights Stack
Multi-Omics AI ChronoGRN · Causal Dynamic GRN Delay-aware, enhancer-gated Neural ODE inferring time-varying gene regulatory networks from paired scRNA+scATAC trajectories Python Neural ODE Multiomics
CompBio & Genomics Single-Cell Foundation Transfer · Multi-Omics Stratification Cross-cohort single-cell embedding transfer under domain shift and multi-omics cancer subtype stratification Python scRNA-seq Genomics
Clinical AI HelixMatch · AURA Clinical · Aegis RAG clinical trial matching engine, RPM sepsis/deterioration predictor, and XGBoost healthcare claims fraud SIU console TypeScript RAG XGBoost
Quant Finance Rust → Quant · Tejas Trading · TradeSim · Orderbook Interactive Rust quant course, Kalshi-style prediction market, Black–Scholes options simulator, and limit order book arbitrage engine Rust C++ TypeScript
AI Security & Arch SyntheticShield · RAGGuard · ModelCardSec · FairDRAM Synthetic data membership-leakage auditing, context-aware RAG privacy firewall, ML security risk cards, and QoS-aware DRAM scheduling Python Security Systems

Technical Stack

  • Languages: C++, Python, Rust, TypeScript, JavaScript, R, SQL, Kotlin, Java, C, LaTeX
  • AI / ML & CompBio: PyTorch, Scanpy, Muon, scvi-tools, Neural ODEs, Graph Neural Networks, XGBoost, RAG / LLMs
  • Web, Data & Systems: Linux, Docker, Git, Next.js, React, Node.js, Tailwind CSS, PostgreSQL, MongoDB, Supabase, AWS

Connect With Me

Popular repositories Loading

  1. trial-matchmaking trial-matchmaking Public

    HelixMatch — AI-powered clinical trial matching engine (RAG)

    TypeScript 2

  2. ChronoGRN ChronoGRN Public

    Delay-aware, enhancer-gated, time-varying gene regulatory network inference from paired scRNA+scATAC trajectories.

    Python 1

  3. salt-cell-demo salt-cell-demo Public

    Interactive demo: how salt sucks water out of cells (osmosis) and why eating salt is dehydrating

    CSS 1

  4. tejas-trading tejas-trading Public

    Tejas Trading — Kalshi-style paper prediction market

    TypeScript 1

  5. SyntheticShield SyntheticShield Public

    Audits memorization and membership leakage in synthetic data generators with canary records, membership tests, and utility panels.

    Python 1

  6. RAGGuard RAGGuard Public

    Context-aware privacy firewall for retrieval-augmented generation (RAG), benchmarked against baseline RAG pipelines.

    Python 1