Experience
My Journey So Far
From Sydney beaches to San Francisco fog. A story of discovering AI safety, taking a leap, and ending up exactly where I wanted to be (even if I didn't know it at the time).
Research Engineer, Alignment Science
Anthropic
San Francisco, CA
Building and running ML experiments to understand and steer the behavior of powerful AI systems. Contributing to exploratory experimental research on AI safety, with a focus on risks from powerful future systems.
- Testing robustness of safety techniques with model organismsā¢
- Running multi-agent RL experiments for scalable oversightā¢
- Building tooling for automated safety evaluationsā¢
- Contributing to alignment assessments and safety casesā¢
The Big Move
Sydney ā San Francisco
12,000 km
Packed two suitcases, said goodbye to Sydney beaches, and moved to a city where the ocean is freezing. Ay nako, the culture shock was real, but so was the opportunity.
- ā¢First time living outside Australia
- ā¢Learned what 'fog schedule' means (still don't understand it)
- ā¢Found the best boba spots in SF (priorities)
- ā¢Miss the beach more than expected ā SF water is cold
Got The Call
Anthropic Interview Process
Sydney, Australia (2am)
What started as 'let me just apply and see' turned into four months of interviews, coding exercises, and increasingly elaborate time zone math. The final call came at 2am Sydney time. I said yes before they finished the sentence.
- Technical interviews that actually tested relevant skillsā¢
- Research presentation to future teammatesā¢
- Time zone coordination that aged me 5 yearsā¢
- The most stressful waiting period of my lifeā¢
Honours Year
UNSW Sydney
Sydney, Australia
The year of 'will this thesis ever end' and discovering that alignment research is what I want to do with my life. Spent more time in the library than my apartment.
- ā¢Thesis on alignment techniques for language models
- ā¢Late nights debugging PyTorch gradient issues
- ā¢Discovered the AI safety research community
- ā¢Realized I'd found my people
The Alignment Rabbit Hole
Self-directed research
Sydney, Australia
Read 'Risks from Learned Optimization' and spent the next three months in an existential spiral. In a good way. Started pivoting everything toward safety research.
- First alignment paper: immediate obsessionā¢
- Started following safety researchers on Twitterā¢
- Attempted to explain AI risk to family (mixed results)ā¢
- Built my first red-teaming experimentā¢
Bachelor of Science
UNSW Sydney
Sydney, Australia
Started as a generic CS student, ended as someone who couldn't stop talking about AI. Classic Kensington campus experience: lectures, boba runs, debugging, late-night gaming, more debugging.
- ā¢First ML course blew my mind
- ā¢Built cursed projects at hackathons
- ā¢Discovered I'm not a systems programmer
- ā¢Night owl tendencies became permanent