Skip to content
View sashikumar6's full-sized avatar
🎯
Focusing
🎯
Focusing
2 followers · 2 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: YOLO

Organizations

@evuventures

Block or report sashikumar6

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
sashikumar6/README.md

Hi, I'm Sashi

LinkedIn Email

SF Bay Area. MS in AI/ML.

I build agentic AI systems and LLM pipelines for enterprise — RAG, multi-agent orchestration, fine-tuning, and everything in between. I go deep on whatever I'm building.

Python LangGraph FastAPI PyTorch AWS Docker

Pinned Loading

  1. Legal-RAG Legal-RAG Public

    Production-grade federal law RAG with multi-source retrieval (U.S. Code, CFR, Case Law), LangGraph orchestration, hybrid search, conflict detection, and Prometheus observability. Regression-tested …

    Python 1

  2. MindTrack-AI MindTrack-AI Public

    Voice-powered mental health and career tracking agent — LoRA fine-tuned GPT-4o-mini, Whisper transcription, ElevenLabs voice response, and Gmail job application tracking

    Python

  3. Rag-eval Rag-eval Public

    Standalone black-box eval harness for Legal-RAG — tests citation accuracy, hallucination rate, and answer relevancy via HTTP. 43-question golden dataset across U.S. Code, CFR, and case law.

    Python

  4. MedBud MedBud Public

    Its a Medical Chatbot Buddy for students who are studying for Medical.

    Python

  5. prompt-me-if-you-can prompt-me-if-you-can Public

    Adversarial AI security game featuring a guarded financial research assistant, hybrid prompt-injection defenses, output scanning, and breach scoring.

    JavaScript

  6. FairVoice FairVoice Public

    HTML