Skip to content
View sanikac10's full-sized avatar

Highlights

  • Pro

Block or report sanikac10

Report abuse

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

Report abuse
sanikac10/README.md

Hi there, I'm Sanika Chavan!

Portfolio

I’m an AI researcher, specializing in LLM training (SFT, RL, IFT, GRPO, DPO), distributed training (PyTorch, Flash Attention, vLLM,, TensorFlow) , studying model behaviour and LLM Security.

Recently, I trained an open-source model that achieved 5% accuracy on the ARC-AGI-2 challenge, a benchmark for testing fluid intelligence in LLMs. This work earned $2,500 worth of compute credits to further iterate and improve the technique.

I thrive at the intersection of cutting-edge research and real-world impact. I enjoy collaborating with cross-functional teams to translate novel AI techniques into scalable, trustworthy solutions. Let’s connect if you’re interested in AI alignment, reinforcement learning, or next-generation language models.

Profile Views 

Pinned Loading

  1. AI-self-healing-security-pipeline AI-self-healing-security-pipeline Public

    Python 2

  2. Annotating-ARC-AGI-2 Annotating-ARC-AGI-2 Public

    Python 2

  3. ConversationalAgent ConversationalAgent Public

    Python 2

  4. nikunj-phutela/CSE576-Project nikunj-phutela/CSE576-Project Public

    Jupyter Notebook 1 3

  5. my-portfolio my-portfolio Public

    HTML 4 1

  6. Orion Orion Public

    Python 1