
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AGI Alignment @ Geodesic Research
My north star is to help make AGI go well for humanity. There are many ways it may not. I don't study them all. My research focuses on developing solutions to the technical and governance challenges. I focus on LLMs because I believe they will lead to AGI and beyond. My current primary research direction is Capability Prevention & Removal (CPR). This multi-paper direction aims to build scalable techniques for removing unwanted capabilities from models before deployment. Crucially, it shouldn't be easy for downstream users to fine-tune models on these capabilities. For instance, we want to be able to prevent models from learning biorisk capabilities in the first place and develop unlearning algorithms to remove any remaining biorisk knowledge from the weights of a fully-trained model. The ability for model providers to control which capabilities their models have would be a significant breakthrough for AI safety. However, this direction may not scale to ASI, and it is best complemented, and hopefully replaced, by breakthroughs in foundational AI alignment. We recently released our first paper in this direction — Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs. We find that we can prevent LLMs from learning about biorisk by filtering pretraining data, and that this is an especially promising intervention for open-weight models. This work has been covered for a general audience by the Washington Post and Fortune. My secondary interests focus on empirically studying self-fulfilling misalignment, safety evaluation data contamination, training open-weight models, and technical AI governance.
University of California, Santa Cruz
Bachelor of Arts - BA, Computer Science
September 1, 2018 – January 1, 2020
Santa Rosa Junior College
Bachelor’s Degree (Transfer), Computer Science
August 1, 2015 – May 1, 2018
Geodesic Research
Founding Member of the Technical Staff
November 1, 2025 – Present
ERA Cambridge
Research Manager - Technical AI Safety
October 1, 2025 – April 1, 2026
ERA Cambridge
AI Safety Research Fellow
June 1, 2025 – October 1, 2025
EleutherAI
Research Scientist
October 1, 2024 – June 1, 2025
Microsoft
Applied Scientist II - Azure AI Platform
June 1, 2024 – January 1, 2025
Redmond, Washington, United States
Microsoft
Applied Scientist II - MSN Trust & Safety
May 1, 2022 – June 1, 2024
Redmond, Washington, United States
Microsoft
Software Engineer II - MSN
November 1, 2021 – May 1, 2022
Redmond, Washington, United States
Microsoft
Software Engineer
July 1, 2020 – November 1, 2021
Redmond, Washington, United States
Microsoft
Software Engineering Intern
June 1, 2019 – September 1, 2019
Greater Seattle Area
remot3.it
Software Engineering Intern
June 1, 2018 – June 1, 2019
San Francisco Bay Area
Remi AI
Software Engineering Intern
March 1, 2018 – June 1, 2018
San Francisco Bay Area
Santa Rosa Junior College
Teaching Assistant, Python
February 1, 2018 – May 1, 2018
opsZero
DevOps Engineering Intern
October 1, 2017 – June 1, 2018
San Francisco Bay Area
Micromat Incorporated
Software Engineering Intern - MacOS
June 1, 2017 – August 1, 2017
San Francisco Bay Area
Cultural Fit Analysis
The candidate has a diverse background spanning large tech companies (Microsoft) and various startups, including AI safety research. This indicates an ability to thrive in different organizational cultures and a breadth of interests. However, the recent shift towards AI safety research might suggest a different primary focus than a pure Backend Engineer role, potentially impacting long-term cultural alignment if the role is not AI-centric. The lack of specific project details for some roles makes it harder to fully assess cultural fit beyond general adaptability.
Soft Skills & Operational Fit
The candidate demonstrates strong soft skills through mentorship, cross-team collaboration, and leadership in critical initiatives. Their experience at startups and large corporations suggests adaptability and a proactive approach to problem-solving. The descriptions highlight an ability to learn quickly and take ownership of projects, which aligns well with operational effectiveness.