Data & ML Engineer

Data & ML Engineer About Atomic Semi Atomic Semi is building a small, fast semiconductor fab. It’s already possible to build this with today’s technology and a few simplifications. We’ll build the tools ourselves so we can quickly iterate and improve. We’re building a small team of exceptional, hands-on engineers to make this happen. Mechanical, electrical, hardware, computer, and process. We’ll own the stack from atoms to architecture. Our team is optimistic about the future and we want to continue pushing the limits of technology. Smaller is better. Faster is better. Building it ourselves is better. We believe our team and lab can build anything. We’ve set up 3D printers, a wide array of microscopes, e-beam writers, general fabrication equipment - and whatever is missing, we’ll just invent along the way. Atomic was founded by Sam Zeloof https://www.youtube.com/@SamZeloof and Jim Keller https://en.wikipedia.org/wiki/Jim_Keller_(engineer). Sam is best known for making chips in his garage, and Jim has been a leader in the semiconductor industry for the past 40 years. About the Team The Fab Software team builds the product that runs our entire fab—a central web app used to manufacture chips. Our users are internal process engineers. We build tools for managing hardware, monitoring and controlling systems in real time, designing processes, and analyzing experimental data. The work on this team spans frontend, backend, and data, all focused on making the fab programmable, observable, and easy to operate as we push toward a fully software-defined chip manufacturing process driven by AI and ML orchestration. About the role We are looking for a senior Data & ML Engineer to build the intelligence layer of our manufacturing process. You will turn raw, messy fab data - telemetry, experiment results, and log - into actionable insights that directly improve our yield, reliability, and throughput. You will know you are successful when process engineers are using the systems and models you’ve productionized to seamlessly identify bottlenecks and optimize the fab in real time. Responsibilities - Lead the design and development of systems to ingest, process, and analyze complex fab data, bridging the gap between hardware telemetry and software control. - Build and productionize applied ML models and simulations to understand manufacturing bottlenecks and optimize the fab's physical throughput. - Develop robust tools for statistical process control (SPC) and real-time process monitoring, breaking down complex manufacturing challenges into actionable data pipelines. - Collaborate closely with process engineers to interpret experimental results, holding yourself and the team accountable to clear timelines for driving physical improvements. - Ensure the reliability of our data architecture, challenging existing assumptions to push the boundaries of what our data systems can achieve. Required Experience - Demonstrated command of applied statistics, data analysis, and building robust data pipelines (batch or streaming). - Experience autonomously leading projects that involve large, messy, and incomplete real-world datasets. - Strong programming proficiency in Python, including libraries like NumPy, PyTorch, or JAX. - A track record of taking ML models out of research and successfully deploying them into real-world production systems. - Exceptional communication skills, with the ability to clearly translate complex data insights into actionable visualizations and technical plans for your team. Nice-to-haves - Experience with simulation, optimization, or real-time control systems. - Familiarity with data orchestration tools (Airflow, Temporal) and large-scale data systems (Spark, S3, etc.). - A deep curiosity or background in manufacturing, physics, or physical systems. Working at Atomic Semi We’re an early-stage hardware startup with solid funding, world-class advisors, and a lab/office in San Francisco, CA. Compensatio ... (truncated, view full listing at source)