Skip to content
View neeraja1504's full-sized avatar
6 followers · 6 following

Achievements

Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Block or report neeraja1504

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 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
neeraja1504/README.md

Hi there 👋 I am Neeraja Kirtane!

I am an AI/ML Research Engineer at MathGPT.ai and a research collaborator with Prof. Kuan-Hao Huang (Texas A&M University). I recently completed my MS in Computer Science at UIUC, where I worked with Prof. Hao Peng and Prof. Dilek Hakkani-Tür.

My research interests lie in mechanistic interpretability, multilingual reasoning, and robustness in LLMs, with a focus on understanding internal model representations and improving model reliability.

I am actively looking for full-time ML/AI research roles in industry or PhD positions in academic labs. If my background aligns with what you're looking for, I’d love to connect!

📫 Reach me at: kirtane.neeraja@gmail.com

Pinned Loading

  1. FactCheckmate FactCheckmate Public

    Forked from deema-A/FactCheckmate

    Preemptively detecting and mitigating hallucinations in LLMs

    Python 1

  2. Maroc Maroc Public

    Evaluating mathematical reasoning chains

    Jupyter Notebook 2 1

  3. Jailbreaking Jailbreaking Public

    Jailbreaking models to produce biased and toxic outputs

    Python 1

  4. hiddenvoices/gpt_finetuning hiddenvoices/gpt_finetuning Public

    Python 1

  5. Bias-mitigation-in-LMs Bias-mitigation-in-LMs Public

    Jupyter Notebook 1