Member of Technical Staff — ML Research, Multimodal
Causal · San Francisco
About this role
## Member of Technical Staff — ML Research, Multimodal ### Mission Help build **general causal intelligence**—AI that can **predict the future** and **identify actions to alter it**. The team is developing a **Large Physics Foundation Model (LPM)** to learn from physical systems where **cause and effect are verifiable** (starting with **weather**). You’ll work on turning **massive, multimodal physical observations** (e.g., sparse sensors, point clouds, hyperspectral imagery, physical fields) into a model that can **predict the future of the physical world**. ### Responsibilities - Design and implement **novel model architectures** and **training algorithms** for learning from massive, multimodal physical data - Solve core physical prediction challenges, including: - Encoding **heterogeneous** and **irregularly-sampled** modalities - Enabling **stable long-horizon rollouts** - Performing **probabilistic forecasting** - Run experiments and ablations that connect **modeling + data decisions** to **predictive skill** (including which data sources/mixtures improve results) - Collaborate across the full ML stack: **data, model, eval, and infrastructure** - Take ideas from **prototype** to **scaled training runs** - Stay current with research and bring new ideas into execution ### What We’re Looking For - A relentless approach to problem-solving, **rapid execution**, and the ability to learn quickly in unfamiliar domains - Strong ML fundamentals, with depth in at least one relevant area (e.g., **sequence/world models, computer vision, sensor fusion, generative modeling, physics-informed NNs**) - Experience training **large-scale models** and analyzing results via **careful ablations** - Familiarity with **distributed training** and scaling **systems considerations** - A track record of turning **open-ended research problems** into **production models**
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.