Transluce

Research Engineer - Scalable Interpretability

San Francisco, USA

Sponsorship not specified$250k-$500kDetected 41 days ago

Machine LearningResearchExperimental DesignCommunication

About the role

As part of our highly collaborative team, you will learn and grow quickly, creating technology at the frontier of AI research and with high direct impact.
This includes: Creating diverse evaluations that range in difficulty.
This involves finding naturally occurring interesting and undesirable behaviors exhibited by open-source models.

Help us develop and train scalable interpretability assistants that can predict and detect unexpected and subtle behaviors from models' activations.
Developing novel architectures and objectives for training interpretability assistants.
Scaling up the training and inference pipelines to support up to 1T-scale models.
good experimental design, epistemic self-awareness and transparency
Core responsibility: Help us develop and train scalable interpretability assistants that can predict and detect unexpected and subtle behaviors from models' activations.

Experience with fine-tuning language models, designing new architectures, and creating evaluations.
Qualities of a strong candidate: Experience with fine-tuning language models, designing new architectures, and creating evaluations.

$250,000 - $500,000/year + benefits Description: Transluce is a non-profit research lab building tools for scalable, end-to-end oversight of AI systems.
We build world-class, AI-backed analysis tools and use these to set industry standards for evaluation.
Our tools are integrated with core agent benchmarks like SWE-bench, while our evaluations are directly underpinning regulation, including our role as EU AI Office's main evaluation developer for harmful manipulation risks.

We are looking for strong scientists and engineers to help advance our vision of scalable end-to-end oversight assistants, building on our recent advances such as predictive concept decoders and user model extractors.

This listing is sourced directly from Transluce's careers page and normalized into a canonical job model.