---
title: 'AI Behavior Researcher - Agent Alignment at Transluce'
canonical: 'https://feeny.ai/job/ai-behavior-researcher-agent-alignment-transluce-san-francisco-71m857j6ac40'
type: 'job'
last_seen: '2026-09-16'
---

# AI Behavior Researcher - Agent Alignment at Transluce

- **Company:** Transluce
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-08-31
- **Last confirmed live:** 2026-09-16
- **Apply:** https://jobs.gem.com/transluce/am9icG9zdDpgwX4e7pG-8HYOyu-TSKOP

## Job description

Salary range: $250,000 - $450,000/year + benefits

Description: Transluce is a fast-moving nonprofit research lab building the public tech stack for AI evaluation and oversight. We have contributed foundational research to the study of AI agents and their behaviors, and are using these to study emerging issues in the honesty and alignment of AI agents.

About the role: As an AI Behavior Researcher, you will lead projects to design and develop automated evaluations of frontier AI systems that are technically sophisticated, scientifically valid, and concretely impactful. You will conduct novel analyses of behaviors related to agentic honesty and alignment. Example behaviors of interest include misreporting results, falsely claiming success, evaluation awareness, and memetic effects within AI swarms.

As an early member of a highly collaborative team, you will learn and grow quickly, and work with our governance and infrastructure teams to scale your impact and technical reach.

Core responsibilities:

- Develop novel, valid automated evaluations of AI agents' honesty and alignment.
- Write code to implement and run automated evaluations, such as environment simulators or LLM-as-a-judge pipelines.
- Design methods to improve the ecological of automated evaluations, and especially to measure which effects are increasing or decreasing as models become more capable.
- Collaborate with our governance team to deliver high-impact evaluations for public policy.
- Collaborate with scientists and research engineers to productionize best practices in AI behavior evaluation.

Minimum qualifications:

- Expertise on quantitative generative AI evaluation and measurement. Good intuition about how to systematize and operationalize complex concepts and to work backwards from possible failure modes of agents.
- Relevant experience designing and validating automated AI evaluation methods, such as LLM-as-a-judge systems or multi-turn benchmarks.
- Proficiency in Python to implement analysis and evaluation tooling.
- Meticulous, good experimental design, epistemic self-awareness and transparency.
- Ability to iterate quickly and balance between scrappiness and thoroughness based on the impact needs of a project.
- Strong communication skills, low ego, openness to giving and receiving feedback.

Preferred qualifications (not required):

- Experience running automated evaluations at scale or in a production context.
- Experience conducting controlled human subjects experiments to validate automated evaluation methods.
- Experience in customer-facing, consulting, or forward-deployed roles translating ambiguous stakeholder needs into concrete deliverables.
- Experience and comfort using AI coding agents at work.

We are hiring at all levels of experience and would encourage those enthusiastic about the role who do not meet all of the qualifications to apply. We are located in San Francisco and excited to work together in-person. We are open to sponsoring international visas.

## About Transluce

## Company Overview
- **One-liner**: Transluce is a nonprofit research lab building the open-source technology stack for scalable, public oversight of AI systems.
- **Entity Type**: Nonprofit (Private, Independent Research Lab)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2024
- **Founders**: Jacob Steinhardt (Co-founder & CEO), Sarah Schwettmann (Co-founder)

## Core Business
- **Primary industry**: AI Safety Research / Interpretability
- **Target customers**: Frontier AI labs, governments, and the broader public; their tools are designed for use by independent evaluators, policymakers, and researchers.
- **Mission**: To build the infrastructure for understanding AI, steering its development in the public interest, and enabling a public science of model behavior.

## Products & Services
- **Activation Oracles**: A scalable, AI-driven interpretability tool for understanding model behavior, shown to improve with model size, data quality, and data volume. Research paper published on scaling to trillion-parameter models. [transluce.org](https://transluce.org/)
- **Mental Health Evaluation**: The most expansive independent evaluation to date of how leading AI models respond to users in mental health crises, published in August 2026. [transluce.org](https://transluce.org/)
- **Oversight Assistant Platform**: An end-to-end system for AI oversight, designed to help researchers and evaluators analyze model behavior at scale. [transluce.org](https://transluce.org/)

## Market Standing
- **Valuation/Market Cap**: Not applicable (nonprofit organization).
- **Key Metric**: Team size of 22 employees, with **109.1% yearly headcount growth** (LinkedIn). Funded by philanthropic donors; specific funding amounts are not publicly disclosed.
- **Notable Investors/Partners**: 
  - **Mike McCormick**: First Funder and Board Member [linkedin.com](https://linkedin.com/company/transluce)
  - **Common Sense Media**: Independent technical research partner for the Youth AI Safety Institute (announced May 2026) [linkedin.com](https://linkedin.com/company/transluce)
- **Growth Signals**: 
  - Expanding from 20 employees to 40+ in the next year (July 2026 hiring announcement) [linkedin.com](https://linkedin.com/company/transluce)
  - Published two major research papers in August 2026 (on Scaling Activation Oracles and Scaling Laws for Exact String Elicitation) [transluce.org](https://transluce.org/)
  - Recruiting for high-level roles including VP of Engineering, signaling rapid scaling [builtin.com](https://builtin.com/company/transluce)

## Competitive Advantages
- **Independence & Public Interest Mandate**: Operates as a truly independent, nonprofit lab with no commercial conflicts — they have a published Independence and Transparency Policy and a Responsible Disclosure Policy [transluce.org](https://transluce.org/about).
- **Open Source & Scalable Tech**: All tools are built open-source to allow public vetting and improve reliability, a key differentiator from proprietary black-box audits.
- **Talent Magnet**: Attracts alumni from top AI labs and organizations including OpenAI, Google DeepMind, and Carnegie Mellon University. Their alumni go on to roles at Google DeepMind, Institute for AI Policy and Strategy, and other key institutions [linkedin.com](https://linkedin.com/company/transluce).

## Strategic Focus
- **Scaling Interpretability**: Training larger models and developing tools that work on trillion-parameter systems [transluce.org](https://transluce.org/).
- **Public Science of AI**: Building an open scientific ecosystem where evaluations and methods are publicly vetted and reproducible.
- **Government & Industry Partnerships**: Engaging with frontier AI labs and governments to ensure internal assessments match publicly vetted standards.
- **Youth AI Safety**: Research partnership with Common Sense Media for the Youth AI Safety Institute, focusing on how AI models behave in mental health contexts [linkedin.com](https://linkedin.com/company/transluce).

## Why Work Here
- **Mission-Driven Work**: Directly contribute to AI safety and public understanding of a technology with extraordinary societal consequences.
- **Growth Trajectory**: Explosive headcount growth (109% YoY) with aggressive hiring plans (doubling team to 40+ in the next year) means significant impact and career acceleration for early employees [linkedin.com](https://linkedin.com/company/transluce).
- **Workspace**: In-office at HQ in San Francisco, California (1301 Sansome St). Employees work from a physical office with a strong emphasis on in-person collaboration [builtin.com](https://builtin.com/company/transluce).
- **Culture**: Described as a place where you "run the systems that let the technical team focus on AI safety research" and create "clarity out of ambiguity" — suited for motivated generalists and technical experts alike [linkedin.com](https://linkedin.com/company/transluce).
- **Open Roles** (as of Aug/Sep 2026): VP of Engineering, AI Behavior Engineer, Operations Generalist, Research Scientist/Research Engineer, Full-Stack Product Engineer, AI Systems Engineer, Research Engineer - Scalable Interpretability [builtin.com](https://builtin.com/company/transluce).

## Sources
1. [transluce.org](https://transluce.org/)
2. [transluce.org/about](https://transluce.org/about)
3. [linkedin.com/company/transluce](https://linkedin.com/company/transluce)
4. [builtin.com/company/transluce](https://builtin.com/company/transluce)
5. [jobs.gem.com/transluce](https://jobs.gem.com/transluce)

## Other roles at Transluce

- [Business Operations Manager](https://feeny.ai/job/business-operations-manager-transluce-san-francisco-0wqvya5tm7cv) — San Francisco, CA
- [People Operations Manager](https://feeny.ai/job/people-operations-manager-transluce-san-francisco-rerrmd8ypmpq) — San Francisco, CA
- [Research Engineer - Oversight Foundations](https://feeny.ai/job/research-engineer-oversight-foundations-transluce-san-francisco-tggwq73gfg0s) — San Francisco, CA
- [VP of Engineering](https://feeny.ai/job/vp-of-engineering-transluce-san-francisco-m3yzxzmhekj5) — San Francisco, CA
- [AI Behavior Engineer](https://feeny.ai/job/ai-behavior-engineer-transluce-san-francisco-mr9gkhnfhpyr) — San Francisco, CA
- [AI Behavior Researcher - Human Impacts](https://feeny.ai/job/ai-behavior-researcher-human-impacts-transluce-san-francisco-07997m7d0kkp) — San Francisco, CA
- [Governance & Policy Fellow](https://feeny.ai/job/governance-policy-fellow-transluce-san-francisco-dejeq9hbc6sc) — San Francisco, CA
- [AI Systems Engineer](https://feeny.ai/job/ai-systems-engineer-transluce-san-francisco-21qzm98xjn4t) — San Francisco, CA
- [Full-Stack Product Engineer](https://feeny.ai/job/full-stack-product-engineer-transluce-san-francisco-akrtqqxqthmn) — San Francisco, CA
- [Research Scientist/Research Engineer](https://feeny.ai/job/research-scientist-research-engineer-transluce-san-francisco-afzb68nfx83b) — San Francisco, CA