Sorcerer is a well-funded, early-stage Y Combinator backed startup. We are hiring a Lead Atmospheric Scientist to be responsible for implementing, troubleshooting, and deploying weather models using a combination of AI/ML and traditional Numerical Weather Prediction.
What You'll Do
- Develop custom weather forecasting models.
- Take end-to-end ownership of models, including deployment on cloud infrastructure.
- Collaborate closely with the product team to develop innovative forecasting solutions.
- Integrate with data assimilation systems to utilize balloon data and other observations.
- Test and validate the accuracy of weather models against real-world data and observations.
What We're Looking For
- 6+ years of experience in Atmospheric Science.
- Experience utilizing open-source numeric weather models like WRF and MPAS.
- Experience operationalizing weather forecast models.
- Experience with multi-dimensional data formats such as Zarr, NetCDF, and GRIB.
Nice to Have
- Experience running both traditional NWP and ML models like GraphCast or Anemoi.
- Comfortable with multi-disciplinary software engineering tooling like Git and Python.
- Extensive experience managing cloud infrastructure (AWS, GCP, Azure).
- Succeed with a high level of autonomy.
- Aren’t afraid of scrappy, unconventional problem solving.
Technical Stack
- Languages/Tools: Python, Git
- Cloud Infrastructure: AWS, GCP, Azure
- Models & Formats: WRF, MPAS, Zarr, NetCDF, GRIB
Team & Environment
You will initially work closely with the CPO, reporting directly to them, with the expectation of later building your own team.
Benefits & Compensation
- Medical, dental, and vision insurance.
- Generous paid time off.
- Lunches provided daily and a stocked office kitchen.
Work Mode
This is an onsite position located in the SOMA district of San Francisco.
We are an equal-opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.



