About You

• build composable, physics-based models that capture real system behavior
• obsess over physical fidelity and numerical stability
• find satisfaction when simulation matches test data
• optimize models for simulation speed
• believe synthetic data is the key to unlocking AI for physical engineering

About Us We are building an engineering AGI. We founded P-1 AI with the conviction that the greatest impact of artificial intelligence will be on the built world. Our first product is Archie, an AI engineer capable of quantitative intuition over physical product domains and engineering tool use. Archie initially performs at the level of an entry-level design engineer but rapidly gets smarter and more capable. We aim to put an Archie on every engineering team at every industrial company on earth.

Our founding team includes the top minds in deep learning, model-based engineering, and industries that are our customers. We closed a $23 million seed round led by Radical Ventures that includes a number of other AI and industrial luminaries (from OpenAI, DeepMind, etc.).

About The Role Our Physical Systems Modeler - 1D Simulation builds the simulators and component models that generate synthetic training data for Archie. You will source or develop first-principles models of thermofluid systems (chillers, air handlers, cooling towers, hydronic networks) and electrical power systems (switchboards, transformers, distribution panels) using acausal modeling frameworks like Julia ModelingToolkit or Modelica.

Your models will be swept across thousands of operating conditions, fault scenarios, and design variations to produce the high-fidelity datasets that teach Archie how physical systems actually behave. This is foundational work: the quality and coverage of your simulations directly determines the reasoning capabilities of our AI. You'll collaborate closely with ML engineers to ensure your synthetic data translates into real-world performance.

What You’ll Do

• Develop acausal component models: Build reusable, parameterized models of HVAC and electrical equipment from first principles that can be used for trade studies.
• Generate synthetic training datasets: Design parameter sweeps and scenario matrices that cover the operating envelope of real equipment, including off-design and fault conditions.
• Validate models against real-world data: Engage with expert engineers for model review, calibrate simulations to manufacturer specs or field measurements from customer deployments.
• Integrate with ML pipelines: Work with AI engineers to format, label, and deliver simulation outputs for model training and evaluation.
• Build and maintain component libraries: Create well-documented, tested libraries that scale across equipment types and can be composed into system-level models.

Who You Are You likely:

• Have built 1D physics-based physics in languages like Julia (ModelingToolkit) or Modelica (Dymola, OpenModelica), Simulink
• Understand thermodynamics, heat transfer, and fluid mechanics at an engineering level
• Can derive governing equations from first principles and implement them numerically
• Have experience with numerical methods for ODEs/DAEs and understand solver trade-offs

You May Also Have

• Experience in Mechanical, Chemical, or Electrical Engineering
• Experience with HVAC system modeling or building energy simulation
• Prior work simulating a large number of system configurations for design space exploration
• Contributed to open-source modeling projects (SciML, OpenModelica, Modelica Standard Library)
• Experience with FMI/FMU model export and co-simulation
• Are fluent in Python for data processing and pipeline integration

Our Values Mission obsession & urgency : We are obsessed with building engineering AGI as quickly as possible. We also recognize that as a startup, speed is our most precious competitive advantage. We are constantly asking ourselves what we can do to go faster. We make tradeoffs and sacrifices (personally and in the workplace) in exchange for speed.

Intellectual excellence & curiosity : We ask “what if?” and experiment liberally. We always look for better ways of doing something. We read voraciously. We challenge each other to be better. We surround ourselves with A players and we actively and unapologetically reject B players (and even B+ players⸺because they tend to surround themselves with C players).

Shipping discipline: We treat production with respect. We test and demo our product constantly. We listen attentively to our customers, users, and stakeholders, and we respect our commitments to them. We also respect our commitments to each other and will go the extra mile (or ten or one hundred) to honor them.

Ownership: We all have significant ownership stakes in the company and operate in founder mode. We believe in hierarchical requirements but not in hierarchical information flows. If we see that something is broken or can be done better, we flag it and we fix it. We encourage each other to play with and fix anything and everything... but there’s a clear owner for everything.

Interview Process

• Initial screening - Head of Talent (30 min)
• Hiring manager interview - Head of Customer Engineering (45 min)
• Technical Interview - with the team (60 min)
• Culture fit & Q/A - with co-founder & CEO (30 min)