Reservoir Simulation Engineer

UniversalAGI

1d•Onsite

About The Position

Engineering simulation is one of the last major categories of software that AI hasn't rebuilt. The tools used to simulate 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), Prith Banerjee (ANSYS CTO), 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). As a Reservoir Simulation Engineer, you'll be in the arena from day one, building the future of AI for physics simulation with your own hands. This is your chance to take everything you've learned building, running, and history-matching reservoir models, conventional and unconventional alike, and use it to generate the high-fidelity simulation data that trains our foundation models for subsurface flow. 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: the weeks lost building and history-matching reservoir models, the manual handoff between geologic modeling and dynamic simulation, and the limits of a single deterministic forecast when the subsurface is anything but certain.

Requirements

3-5+ years of industry hands-on experience building and running reservoir simulation models, including conventional (blackoil and compositional) and unconventional reservoirs, from model construction through history matching, forecasting, and optimizing field development
Expert in reservoir simulation frameworks (Eclipse/Intersect, CMG, OPM Flow, or similar), including blackoil and compositional formulations
Deep understanding of reservoir engineering fundamentals: PVT behavior, relative permeability and capillary pressure, well modeling, material balance, and history matching
Solid understanding of the static-to-dynamic model handoff: geologic and geocellular model construction, upscaling, and grid generation
Strong communicator capable of bridging customers, engineering and research teams
Outstanding execution velocity and delivery
Exceptional creativity, problem-solving ability, ambition, and attention to detail
Comfortable working in high-intensity, fast-paced startup environments with evolving priorities and tight deadlines

Nice To Haves

Working proficiency in Python (or similar) for scripting, automating simulation pipelines, and structuring simulation output into clean, well-labeled datasets
Prior experience integrating AI/ML models into reservoir workflows, or generating simulation datasets specifically intended to train or validate machine learning models
Experience with probabilistic or ensemble history matching, uncertainty quantification, or geostatistical modeling (Gaussian processes, kriging)
Experience modeling unconventional reservoirs: multi-stage hydraulic fracturing, complex fracture networks, and the production-decline behavior distinct from conventional plays
Master's or PhD in Petroleum Engineering, Reservoir Engineering, Geology, or a related field
Domain expertise in geothermal, or other subsurface flow applications adjacent to oil and gas
Experience at high-growth AI startups (Seed to Series C)
Forward deployed experience working directly with customers to solve their hardest problems

Responsibilities

Design, build, and run reservoir simulation studies, both blackoil and compositional models, across conventional and unconventional reservoirs, at unprecedented scale and speed
Come up with creative ways to construct reservoir models, simulate hundreds or thousands of reservoir model variants systematically, building the data pipelines that will train our foundation models
Guide the development of our product and our revolutionary new AI models for physics by working directly on research problems with our AI team, bridging the gap between traditional reservoir simulation and cutting-edge ML
Work directly with clients to solve their problems and define benchmark datasets, validation criteria, and workflows that prove our models can match or exceed traditional reservoir simulation accuracy
Generate high-quality simulation data at scale; every simulation you run directly improves our foundation models
Advise the AI research team on the nuances that matter: PVT behavior and fluid characterization, relative permeability and capillary pressure, history matching and uncertainty quantification, multi-stage hydraulic fracturing and complex fracture networks, and the production-decline behavior that separates unconventional reservoirs from conventional ones
Lead technical customer conversations with customers and internal teams, translating between the world of reservoir engineering and the world of AI