AI and Computational Geometry Engineer

Atomic Machines•Emeryville, CA

2d•$200,000 - $250,000•Onsite

About The Position

Atomic Machines is a company pioneering micromanufacturing with its Matter Compiler™ technology platform. This platform enables the design and construction of new classes of micromachines by offering manufacturing processes and a materials library beyond the scope of traditional semiconductor manufacturing. It opens up MEMS manufacturing for device classes previously impossible to produce and for entirely new categories. The Matter Compiler™ technology platform is a programmable digital platform, similar to 3D printing, but it is a multi-process, multi-material system that produces complete, functional micromachines from digital inputs and raw materials. The company has developed an initial device, made possible by this technology, which is soon to be unveiled. This role focuses on the Design for Manufacturing (DFM) aspect within the Atomic Machines CAM stack. The primary responsibility is to translate device designs into manufacturable geometry by encoding engineering judgment about arrangement, holding, and processing as software. This involves owning the full DFM layer, which includes the geometry between the device model, workpiece, and machine processes. It also encompasses how parts are arranged on a blank, held during cutting, the DFM rules for supported processes and materials, constraints and checks for designers, and physical models that underpin these rules. The ideal candidate is an engineer who thinks in terms of manufacturing constraints and writes code that adheres to them, bridging the gap between design engineers with unbuildable geometries and process engineers with unexpected machine results. This role operates within a cross-functional team including AI, Modeling and Simulation, Design, and Process Engineering.

Requirements

Minimum of 5 years of relevant industry experience or a PhD in a related field.
Practical DFM experience, demonstrated by writing code that generates geometry under real manufacturing constraints (e.g., slicer/toolpath software, sheet metal stamping design software, PCB/lead frame layout, design automation).
Working computational geometry ability, including 2D boolean operations, polygon offsetting, and packing/no-fit-polygon reasoning.
Strong software engineering skills in Python and a systems language.
Comfort driving geometry kernels and libraries through their APIs (e.g., Shapely, Clipper, OpenCascade, CGAL).
Demonstrated ability to work productively on novel, poorly specified problems (e.g., through a PhD, open-source contributions, patents, or greenfield industry work).
Willingness to ground work in physical evidence from the fab and iterate with process engineers.
Bachelor's, Master's, or PhD in Mechanical Engineering, Computer Science, Applied Math, Computational Design, or a related field.

Nice To Haves

Exposure to laser micromachining or other subtractive micro-scale processes (kerf, heat-affected zone, tabbing, part release).
Background in mechanics to reason about part stability during processing, or the interest to develop this with the Modeling and Simulation team.
Experience with combinatorial and geometric optimization (MILP, constraint programming, metaheuristics).
Experience with machine learning on geometric data (e.g., learned models over meshes/B-rep graphs, neural fields, learning from expert demonstration).
Experience placing heuristic or learned components within a deterministic, auditable pipeline, including validation and fallback behavior.
Familiarity with CAE tools (e.g., Comsol, Ansys, Abaqus).
Contributions to open-source geometry or manufacturing software.

Responsibilities

Develop DFM as a software capability, including algorithms, representations, and constraints to convert device geometry into process-executable geometry.
Implement manufacturability constraints within the design loop to ensure infeasibility is identified at the design stage.
Formalize and codify the judgment of design and process engineers into auditable and testable software.
Collaborate with the Modeling and Simulation team to ground DFM decisions in the mechanics of the process.
Define correctness criteria for layouts and test against fab runs, incorporating failures back into constraints and models.
Build a knowledge base from production history to support calibration, regression testing, and potentially learned components.