Expert: Software Engineer – AI Evaluation (Task-based Contract, Remote)
Patronus AI · Remote - India
Applied AIremoteexpert$104k–$208k
At a glance
Highlights
- Design realistic, multi-step tasks to challenge frontier AI models.
- Judge how AI handles code, reasoning and technical instructions.
- Help advance simulation research toward human-aligned AGI.
What they offer
- Flexible 15-20 hours per week
- Can be done alongside a full-time job
- Hourly project-based contract
Ideal candidate
Experienced software engineer who loves dissecting code quality and reasoning. Detail-oriented, independent and motivated to stress-test frontier AI to reveal real engineering strengths and gaps.
Requirements
- 2+ years professional software engineering experience (internships excluded)
- Experience with system design, data pipelines, ML or LLM-based applications
- Prior work in code review, technical writing, AI training or model evaluation
- Strong coding skills in Python, Java, C++, JavaScript, TypeScript or Go
- Experience building, reviewing and debugging production-grade code
- Ability to follow technical guidelines, work independently and meet deadlines
- Excellent written communication and attention to detail
- Bachelor's in computer science, engineering or related field or equivalent experience
- remote policy
- Fully remote within India
- hiring process
- Applications reviewed on a rolling basis with placement based on project needs and assessment results
Lab profile
About Patronus AI
Frontier lab developing simulation research and infrastructure for human-aligned AGI.
Known for
- Pioneering AI evaluation research
- Simulation research and infrastructure
- Creators of FinanceBench
Posted · Last seen