Sep 2024 – Present · 1 yr 8 mos

• Researcher on the JEPA team for video understanding, building interpretable and physically plausible world models. Leads 160+ member interpretability forum across FAIR, Reality Labs, and GenAI.

Jun 2024 – Aug 2024 · 2 mos · Berkeley, California, United States · On-site

• Researching vision sparse autoencoders (SAEs) and interpretability with Lee Sharkey in MATS cohort.

Jan 2024 – Mar 2024 · 2 mos

• Researching vision mechanistic interpretability with Neel Nanda. Built the Prisma library, an open source library for vision mechanistic interpretability and sparse autoencoders.

Sep 2023 – Present · 2 yrs 8 mos · Montreal, Quebec, Canada

• Research on understanding the internal function of world models and multimodal models.
• Advised by Professor Blake Richards at McGill's LiNCLab and Dr. Mike Rabbat at Meta.

Nov 2021 – Present · 4 yrs 6 mos

Sep 2021 – Jan 2023 · 1 yr 4 mos · San Francisco Bay Area

• Co-founder and CTO. Transitioned to strategic advisory role after successfully guiding company through initial growth stages.

Jul 2021 – Oct 2021 · 3 mos

Dec 2020 – Feb 2021 · 2 mos · Palo Alto, California, United States

• Cohort 6

Aug 2020 – Jun 2021 · 10 mos

• Designed and implemented an end-to-end analysis pipeline for receptive field analysis from calcium imaging data in mouse visual cortex at the Stringer Lab
• Created internal Python library and GUI for receptive field analysis and exploration
• Built a versatile tool that researchers can use through a visual interface or code
• Conducted comparative analysis between mouse visual cortex data and optic flow neural nets.
• Specialized in deep learning and neuroscience data analysis, scientific software development, and computational modeling of visual systems

May 2020 – Aug 2020 · 3 mos

• Led intern research team in evaluating and benchmarking GPT models trained on specialized datasets
• Optimized pipeline accuracy by 10% through dataset curation and benchmarking
• Specialized in LLM training, pretraining, and evaluation techniques
• Conducted novel research on improving LLM training methods, including exploration of RL-based approaches and tokenizer optimization
• Engineered critical components of a RAG-like system for long-form document retrieval, serving banks and B2B clients
• Optimized database latency, improving stack efficiency by 30%
• Contributed to core organizational processes and published research findings on company research blog

Sep 2018 – May 2019 · 8 mos · Princeton University, NJ

• Wrote thesis on semantic representation in the human brain in collaboration with the Princeton Neuroscience Institute and Google.
• Leveraged knowledge of data science and machine learning, including methods like PCA and multivariate regression, and Python libraries like Tensorflow, NumPy, scikit-learn, and pandas, to analyze neural response.

Jun 2018 – Aug 2018 · 2 mos · Greater New York City Area

• Leveraged knowledge of dynamical systems to build models of the homebuilding market.

Oct 2017 – Jul 2018 · 9 mos · Princeton, New Jersey

• Analyzed financial health of companies for Princeton's only investment organization that donates returns to charity.

May 2017 – Aug 2017 · 3 mos · Cambridge, Massachusetts

• Built database of ethnographic information for the Natural History of Song Project.
• Implemented web scraper saving 15 hours/week.

Apr 2016 – Nov 2016 · 7 mos · Princeton University

• Made executive decisions for student-run three-day tech conference on nanotechnology, artificial intelligence, genetic engineering, VR/AR, and nuclear fusion, attended by 154 funded student entrepreneurs, award-winning STEM grads and undergrads, and published PhDs from top universities.
• Led campaign that increased membership from 70 to 250+ within one year, and organized the recruitment and orientation of 20+ directors.
• Ran strategy to promote artificial intelligence safety to international conference attendees and the Princeton student body.

Jun 2013 – Aug 2013 · 2 mos · Boston, MA

• Designed a pilot study on the correlation between air quality and mood in Boston, analyzed data statistically, created air quality activities and presentations for museum guests, and presented results of study in an interactive public forum of policymakers, city planners, scientists, museum staff, and citizens.