Safety Jevroni (Contract, 6 weeks)
Join TypeSafe as a safety researcher for a 6-week contract focused on AI safety and model evaluation.
Posted by employer 2 weeks ago
First seen on Joblaze 2 hours ago
Last verified on the company career page 2 hours ago
Skills & Technologies
What you'll build
- Build evals and investigate model behavior
- Keep a document of observations
- Write a departure post
Must have
- Strong research background in AI safety
- Experience raising concerns in writing
AI in the day-to-day
null
Not disclosed in this posting: compensation, seniority, years of experience, work arrangement, visa sponsorship.
Joblaze summary
In this short-term contract role, the safety researcher at TypeSafe AI focuses on evaluating model behavior and raising concerns about AI safety during team discussions. Candidates should have a solid background in AI safety and experience in model evaluation, along with the ability to communicate concerns effectively. This position is suited for individuals who are comfortable navigating complex ethical discussions and can handle the pressures of a fast-paced AI lab environment. The role offers a unique glimpse into the inner workings of a startup backed by significant funding.
Joblaze insights
- Listed today — first seen on Joblaze October 19, 2026. Last confirmed on TypeSafe AI's careers page October 19, 2026.
- AI/ML appears in 46.1% of 1766 comparable ai/ml roles in United States.
Quick facts
- What's the tech stack?
- Joblaze extracted these technologies from the posting: AI/ML.
- Is this full-time or contract?
- Contract for this Safety Jevroni (Contract, 6 weeks) role at TypeSafe AI.
From the original posting
We're looking for a safety researcher to join TypeSafe, get increasingly quiet in meetings, and quit about six weeks later because they're disturbed by what they've seen.
What you'll do
Build evals and investigate model behavior that concerns you.
Ask “should we?” in meetings scheduled to discuss “how soon?”
Keep a document that starts as “Initial observations” and ends as “For the record.”
Write a departure post that makes people concerned enough to share it, despite containing almost no information.
What you bring
A strong research background in AI safety, alignment, interpretability, or model evaluation.
Experience raising concerns calmly, then in writing.
The ability to say “I can't discuss specifics” and somehow make things worse.
A sincere belief that you can change things from the inside. We'll need that for the first two weeks.
Your first (and only) six weeks
Weeks 1–2: Get set up, meet the team, and tell your friends the work is fascinating.
Weeks 3–4: Request additional access. Receive it. Stop telling friends about work.
Weeks 5–6: Write a long internal memo. Take a walk. Decide you won't be coming back on Monday.
You'll be working with people you'll later describe as “some of the most talented people I've ever worked with.”
To apply, submit a draft of your eventual resignation post. You may omit specifics.
Standard company text repeated across TypeSafe AI's postings is omitted here.
Similar positions
Explore more