About this job
<h2>About us</h2><p style="min-height:1.5em">AIM Solutions is an early-stage deep-tech startup in Eindhoven building inspection and metrology equipment for the semiconductor industry. We are in active build phase, small, and growing.</p><h2>The role</h2><p style="min-height:1.5em">You will own the algorithms at the core of our instrument: the GPU-accelerated engine for phase retrieval and wafer metrology. This is the deep end of computational imaging, where progress comes from understanding both the optimization and the physics.</p><p style="min-height:1.5em">Concretely, you will:</p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Develop and maintain our GPU-accelerated computational imaging engine for phase retrieval</p></li><li><p style="min-height:1.5em">Improve reconstruction quality, convergence, and robustness across varied and imperfect datasets</p></li><li><p style="min-height:1.5em">Design and implement new reconstruction methods: physics-based differentiable forward models, regularization and constraint schemes for ill-posed problems, and support for new acquisition modes</p></li><li><p style="min-height:1.5em">Translate methods from the literature and from our own ideas into tested, performant code</p></li><li><p style="min-height:1.5em">Use physical insight into the optical system to decide how to change the algorithm so that results improve</p></li><li><p style="min-height:1.5em">Profile and optimize the engine for GPU performance on large datasets</p></li></ul><h2>Your profile</h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em">A PhD, or equivalent research depth from industry, in a physics-heavy or numerically heavy field</p></li><li><p style="min-height:1.5em">Several years developing numerical or scientific algorithms, ideally in imaging, inverse problems, or a comparable domain</p></li><li><p style="min-height:1.5em">Strong numerical optimization, both gradient-based and iterative methods</p></li><li><p style="min-height:1.5em">Working knowledge of Fourier optics and wave-propagation physics</p></li><li><p style="min-height:1.5em">Strong Python and array programming, with experience in GPU frameworks such as JAX, PyTorch, TensorFlow, or CUDA</p></li><li><p style="min-height:1.5em">You write tested, maintainable code that others can build on</p></li><li><p style="min-height:1.5em">You can reason from physics to algorithm and back, and judge what will improve a reconstruction</p></li><li><p style="min-height:1.5em">Technical curiosity; we will teach you the specifics of our computational imaging approach</p></li><li><p style="min-height:1.5em">Full professional proficiency in English</p></li></ul><p style="min-height:1.5em"><strong>Bonus experience in any of these:</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Phase retrieval, coherent diffractive imaging, holography, or tomography</p></li><li><p style="min-height:1.5em">Physics-informed machine learning, differentiable forward models, automatic differentiation</p></li><li><p style="min-height:1.5em">Regularization and constrained optimization for ill-posed inverse problems</p></li><li><p style="min-height:1.5em">High-performance and GPU computing with performance profiling</p></li><li><p style="min-height:1.5em">Linux development environments</p></li></ul><p style="min-height:1.5em">This is a senior, research-to-production role. We expect a track record of taking new methods from concept to working, maintained code that runs in a real instrument.</p><h2>What we offer</h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Ownership of the reconstruction algorithms at the heart of a tool that does not exist anywhere else yet</p></li><li><p style="min-height:1.5em">Small team, short feedback loops, an open environment to have real impact</p></li><li><p style="min-height:1.5em">Competitive salary for the Dutch market</p></li></ul><p>Find <a href="https://www.arbeitnow.nl">Jobs in Netherlands</a> on Arbeitnow</a>