Skip to content
View sririthishpalani-max's full-sized avatar

Highlights

  • Pro

Block or report sririthishpalani-max

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
sririthishpalani-max/README.md

Hi, I'm Sri Rithish Palani

CS @ Georgia Tech building AI/ML and software systems — with a side interest in quantitative trading.

I like building systems that actually run end to end — LLM/RAG applications, evaluation tooling, and the occasional always-on trading bot. Currently looking for AI/ML & software engineering internships/co-ops (Fall 2026).

Featured projects

Project What it is Stack
JavaDocRAG Retrieval-augmented Q&A over the JDK 25 API docs — hybrid BM25 + dense retrieval, cross-encoder reranking, cited answers Python · FastAPI · FAISS · Claude
kalshi-latency-arb Async latency-arbitrage system for the CFTC-regulated Kalshi event-contract exchange — quarter-Kelly sizing, risk controls, backtester Python · asyncio · WebSocket
ibkr-dual-ema-trading Session-aware Dual-EMA crossover trading system for Interactive Brokers — real-time bars, order-lifecycle management, risk controls, Telegram control, backtester Python · ib-insync · asyncio
llm-guided-evolution Research (GT VIP lab) — LLM inference optimization within the Guided Evolution LLM + genetic-algorithm NAS framework; quantization, RAG, distributed runs on PACE/SLURM Python · PyTorch · SLURM/HPC

What I've worked on

  • Software Engineering Intern @ OpsNerve.ai — built an LLM-powered root-cause-analysis agent (prompt pipelines + evaluation harness) for an AIOps incident platform.
  • Undergraduate Researcher, GT VIP (Automated Algorithm Design) — LLM quantization and RAG-retrieval experiments inside an evolutionary-algorithm framework, running distributed jobs on Georgia Tech's PACE HPC cluster (SLURM).
  • Personal projects — RAG systems and quantitative/automated-trading infrastructure (see pinned repos).

Tech I work with

Python · Java · C · SQL · JavaScript ML/AI: PyTorch · RAG pipelines · LLM evaluation · quantization · scikit-learn Systems: Linux · SLURM/HPC · Docker · Git · SQLite · REST APIs

Connect

Pinned Loading

  1. JavaDocRAG JavaDocRAG Public

    RAG system that answers Java/JDK 25 API questions with cited, source-grounded answers — hybrid BM25 + dense retrieval, cross-encoder reranking, and Claude.

    Python

  2. kalshi-trading-system kalshi-trading-system Public

    Real-time, async event-contract trading system for the Kalshi exchange — WebSocket market data, layered risk controls, RSA-PSS-signed API execution, and a reproducible backtester (Python, asyncio).

    Python

  3. ibkr-dual-ema-trading ibkr-dual-ema-trading Public

    Session-aware Dual 5-min EMA crossover trading system for Interactive Brokers (ib-insync) — real-time bar aggregation, order-lifecycle management, layered risk controls, Telegram control, and a par…

    Python

  4. llm-guided-evolution llm-guided-evolution Public

    Research showcase — LLM inference optimization within the Guided Evolution (LLM + genetic-algorithm NAS) framework at Georgia Tech's VIP Automated Algorithm Design lab. Links to the team codebase; …

  5. NeelMaddu268/CS2340_F25_Team6 NeelMaddu268/CS2340_F25_Team6 Public

    Java