📍 San Francisco | 🏢 5 Days Onsite

Location: Onsite in San Francisco

Compensation: Competitive Salary + Equity

Geophysics + Seismic Researcher

Who We Are

Engineering simulation is one of the last major categories of software that AI hasn't rebuilt. The tools used to design aircraft, ships, reservoirs, and medical devices still run on numerical methods that are decades old, and an engineer can wait a full day for a single answer. UniversalAGI is building foundation models that learn physics directly from data, and they are already running in early deployments on real computational fluid dynamics and reservoir engineering problems for some of the largest industrial and defense organizations in the world.

We are a team of 25 researchers and engineers in San Francisco backed by Elad Gil (#1 Solo VC), Eric Schmidt (former Google CEO), Ion Stoica (Databricks Founder), Jared Kushner (former Senior Advisor to the President), David Patterson (Turing Award Winner), and Luis Videgaray (former Foreign and Finance Minister of Mexico).

About the Role

As a founding Geophysics + Seismic Researcher, you'll be in the arena from day one, at the exact intersection where deep learning meets subsurface physics. This is your chance to take everything you've learned across seismic processing, interpretation, and geologic modeling and use it to build foundation AI models that transform how the energy and subsurface characterization industries work.

You'll work directly with the CEO and founding team to shape our product around the real pain points you've faced in your career: manual and compute-intensive seismic interpretation, slow full waveform inversion, and the disconnect between geophysical models and the petrophysical properties that actually drive decisions.

What You'll Do

Develop novel AI architectures for subsurface physics, including transformer-based and and generative neural operators for seismic modeling, inversion, and geologic interpretation

Own research workflows end to end: synthetic data generation (procedural subsurface/geology models, forward simulation), model training, validation, and deployment

Apply statistics and uncertainty quantification, including Bayesian and generative modeling, to represent multiple plausible subsurface realizations rather than a single deterministic answer

Work hands-on with seismic processing, full waveform inversion (FWI), and geologic modeling, and help connect velocity/density models to the petrophysical properties (porosity, permeability, lithology) that matter for reservoir and geologic decisions

Run large-scale experiments on seismic and geologic datasets, iterate rapidly on model performance, and help drive the research roadmap based on what actually works

Collaborate directly with domain experts and customers in energy, subsurface characterization, and related industries to understand workflows, pain points, and validation criteria

Publish and present breakthrough results, internally and externally, as we push the boundaries of AI for subsurface physics

Move fast and ship: take research from idea to production-ready model in weeks, not months, and see your work deployed to real customers

Qualifications

PhD in Geophysics or a related engineering discipline, with extensive experience in seismic processing and interpretation

Strong AI background, including models for physical systems such as FNO and Transolver

Experience in statistics and uncertainty quantification; familiarity with seismic interpretation, full waveform inversion, and geologic modeling

Proficient in Python and ML frameworks, able to independently own workflows from synthetic data generation through model training

Bonus Qualifications

Published research in top-tier geophysics or ML venues (e.g., Geophysics, JGR, NeurIPS, ICML, ICLR)

Experience with generative modeling for geology (e.g., 3D subsurface realizations) and geostatistics (Gaussian processes, kriging)

Background in adjacent physical-systems or earth-science modeling domains (e.g., oceanography, geospatial science, other geophysical inversion problems)