Winter Research Engineer Co-op

Anduril Industries is a defense technology company with a mission to transform U.S. and allied military capabilities with advanced technology. By bringing the expertise, technology, and business model of the 21st century’s most innovative companies to the defense industry, Anduril is changing how military systems are designed, built and sold. Anduril’s family of systems is powered by Lattice OS, an AI-powered operating system that turns thousands of data streams into a realtime, 3D command and control center.

As the world enters an era of strategic competition, Anduril is committed to bringing cutting-edge autonomy, AI, computer vision, sensor fusion, and networking technology to the military in months, not years.

Maritime Digital Production is the software and digital systems function within Anduril's Heavy Metal division. We build and deploy the technology stack that powers Anduril's shipbuilding factories: the data infrastructure that makes every machine and sensor visible in real time, the manufacturing execution system that workers and planners use every shift, the scheduling engine that replans production in minutes instead of days, and the AI systems that remove manual toil from the shop floor and business operations.

That includes Serapis, our program building components for the Virginia-class submarine.

We operate at the boundary between Operational Technology and Information Technology, incubating solutions close to the production line, validating them with real operators, hardening them for reliability and security, and scaling them across sites. The environment is fast, physical, and consequential. When our systems go down, production stops. The output of our work is not a dashboard: it is a ship.

We are scaling from a founding team to more than 70 engineers across multiple U.S. sites. As an intern you join early, on a problem that matters to production, with a defined project and a named engineer you work with every day.

We have built a computational geometry engine that takes a 3D CAD assembly and works out the orders in which it can physically come apart, and therefore the orders in which it can be built. It finds where parts touch, builds directional blocking graphs from that contact geometry, searches for collision-free removal directions, and produces the precedence constraints our production scheduling system plans against.

It works on small and mid-sized assemblies. It needs to work on the assemblies we actually build, which have hundreds to thousands of parts. Your job is to close that gap.

This is algorithms engineering with a research flavor. You will profile the engine on real assemblies, find where the time and memory go, and attack it: search ordering, pruning, memorization, incremental updates, subassembly decomposition, and parallelism. The goal is a measurably faster engine rather than a paper, and every result is held to one rule: a faster answer that is a different answer is a bug.

• Profiling a C++ computational geometry pipeline on real assemblies and reporting where time and memory go
• Designing and implementing algorithmic improvements to a disassembly sequence search: candidate ordering, pruning, memoization, and incremental graph updates
• Decomposing large assemblies into subassemblies that can be solved independently
• Parallelizing expensive geometric tests across cores without losing determinism
• Building a benchmark corpus and harness that run in continuous integration and catch regressions
• Gating every optimization on output equivalence against a reference set
• Writing up results and presenting them to the engineering team

• Must be pursuing master’s degree or PhD in Computer Science, Robotics, Mechanical Engineering, Applied…