About the CompanyAn early-stage AI research lab focused on interpretability, alignment, and reinforcement learning is hiring a Research Engineer. Founded by former frontier-model researchers, the team works directly on model internals and training dynamics to better understand how AI systems reason. The lab runs fast experimental research cycles, building custom tools to explore open-ended questions about model behavior.About the RoleThis role focuses on building the experimental tooling that enables interpretability research. You will develop systems that allow researchers to inspect, measure, and manipulate internal model representations. This is not a production ML or MLOps role — it’s for engineers who enjoy building new experimental systems from scratch and working closely with researchers.ResponsibilitiesBuild custom RL-style environments and experimental testbeds for interpretability researchDevelop tools for activation tracing and mechanistic interpretabilityImplement probes to detect latent concepts (e.g., deception, goals, uncertainty)Prototype activation-level steering methods beyond prompting or fine-tuningCollaborate with researchers to rapidly iterate on experiments and toolingQualificationsStrong programming skills in PythonExperience with ML frameworks such as PyTorch or JAXExperience working with deep learning models or LLMsStrong software engineering fundamentals and ability to build experimental ML systemsPreferred SkillsExperience in mechanistic interpretability or alignment researchFamiliarity with reinforcement learning environmentsBackground working with model internals, representations, or probing methodsResearch experience (PhD preferred but not required)Pay range and compensation packageCompetitive salary, equity, and benefits.