Skip to content
View greninja's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report greninja

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
greninja/README.md

Hi there 👋

I come from a research background 🧪 with hands-on experience building open source software 💻. I earned my Master’s in Computer Science, where my work on trustworthy machine learning earned a Spotlight acceptance at NeurIPS 2024 (Link). You can find more about my work and projects here and on my webpage (link on the left).

🌱 I’m now looking to transition into a more engineering-focused role—ideally at an early- to mid-stage startup where I can have a tangible impact on growth. While much of my recent work has been in ML research on security and privacy, what truly drives me is engineering: building scalable systems and solving complex, ambiguous problems. That passion is what led me to study computer science and engineering in the first place, and it’s what I want to focus on in the years ahead. I value engineering cultures that foster both personal and professional growth, and I’m open to working across domains as long as the product is compelling, the team is strong and dynamic, and there’s room to learn and make an impact.

🔭 To support this shift, I’ve been diving into side projects to sharpen my systems design skills—combining reading with small-scale builds to better understand trade-offs and architectural choices. I’m especially interested in infrastructure and system-level challenges in deploying large language models (LLMs) at scale. Recently, I built an LLM cache to intercept and reuse responses for repeated or similar queries, cutting down on redundant computation and improving inference latency.

Pinned Loading

  1. adaptive-randomized-smoothing adaptive-randomized-smoothing Public

    Forked from ubc-systopia/adaptive-randomized-smoothing

    Python

  2. NPLM NPLM Public

    Neural Network for word embeddings and Language Model

    Python 6 5

  3. javaminining javaminining Public

    Code to scrap git repositories and fetch commits (wherein new function arguments are added) using PyDriller

    Python

  4. ml_privacy_meter ml_privacy_meter Public

    Forked from privacytrustlab/ml_privacy_meter

    Machine Learning Privacy Meter: A tool to quantify the privacy risks of machine learning models with respect to inference attacks

    Python

  5. llm_cache llm_cache Public

    A simple, lightweight LLM cache using Redis to reduce latency and improve throughput

    Python

  6. cuda_programs cuda_programs Public

    CUDA programming examples and implementations

    Cuda