Member of Technical Staff — Research Engineering, Evaluation
Causal · San Francisco
About this role
## Mission We’re building **general causal intelligence**—AI that can both **predict the future** and **identify actions to alter it**. To do this, we’re developing a **Large Physics Foundation Model (LPM)**, grounded in the idea that physical systems have **verifiable cause and effect**. We’re starting with **weather**, and our founding team has built and deployed AI in the physical world across **robotics, drug discovery, and particle physics** (e.g., DeepMind, Waymo, Cruise, Insitro, Nabla Bio, CERN). ## Role: Member of Technical Staff — Research Engineering, Evaluation Your mission is to build the **central evaluation framework** that the entire research organization runs on—covering **pipelines, metrics, and tools** that turn results into shared, trustworthy understanding. ## Responsibilities - Design and build a **central, reusable evaluation framework** used by every model and team - Implement **evaluation pipelines**, **benchmark suites**, and **baselines** to measure and compare model quality across efforts - Build **visualization and dashboard tools** that convert raw results into shared, actionable insights - Establish **sound statistical methodology** so teams can distinguish real improvements from noise - Partner with research and domain teams to translate what “good” means into **standardized, automated metrics** ## What We’re Looking For - A relentless approach to problem-solving, **rapid execution**, and fast learning in unfamiliar domains - Strong software engineering skills; experience building **data/evaluation pipelines at scale** - Experience turning research/model outputs into **metrics, benchmarks, and visualizations** teams rely on - Solid grasp of **probability and statistics**, with judgment to design evaluations that measure what they claim - **Full-stack** capability: comfortable building both backend pipelines and frontend tools people use to interpret results - Ability to **own deliverables end-to-end**, from requirements through autonomous execution
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.