Research Engineer - Oversight Foundations
Transluce is an independent San Francisco 501(c)(3) nonprofit research lab building open technology and research infrastructure for scalable oversight and understanding of AI systems.
Funding history
About Transluce
Transluce develops research, platforms, and open-source tools intended to help evaluators and other stakeholders understand, measure, and steer advanced AI behavior in the public interest. Its active product, Docent, analyzes AI-agent transcripts using traceable behavior rubrics, qualitative review, and quantitative analysis.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop and train scalable oversight assistants that predict and detect unexpected AI system behaviors. You will create diverse evaluations, identify undesirable open-source model behaviors, develop training architectures and objectives, and scale training and inference pipelines for very large models.
Requirements
- Language model fine-tuning
- Architecture design
- Evaluation design
- Experimental design
- Programming
- Maintainability
- Communication skills
Responsibilities
- Develop and train scalable oversight assistants
- Create evaluations across a range of difficulties
- Identify interesting and undesirable behaviors in open-source models
- Develop architectures and objectives for oversight-assistant training
- Scale training and inference pipelines for large models
Benefits
- International visa sponsorship