Staff Applied ML Engineer
About Us We are Sila, a next-generation battery materials company. Our mission is to power the world’s transition to clean energy. To create this future, our team is building a better lithium-ion battery from the inside out today. We engineer and manufacture ground-breaking battery materials that significantly increase the energy density of batteries, while reducing their size and weight. The result? Smaller more powerful batteries that can unlock innovation in consumer devices and accelerate the mass adoption of electric cars to eliminate our dependence on fossil fuels. We're tackling one of the biggest challenges of our time every day, and together we're redefining what's possible. Are you ready to be a part of a team committed to changing the world?Who You Are You are excited to build the intelligence layer for manufacturing operations: systems that help the factory understand what is happening, predict what is likely to happen next, and respond earlier and better as a result. You are a strong technical builder who likes hard problems with real operational consequences. You can take an ambiguous manufacturing problem and turn it into a working system that engineers and operations teams actually use. You are comfortable working across software, data, engineering logic, and manufacturing systems. You know how to deal with noisy plant data, imperfect systems, and messy failure modes. You do not stop at visibility. You build systems that drive action. We are looking for someone who has built and shipped systems that changed how an operation runs. Build Manufacturing Intelligence Systems Build in-house production systems that ingest plant telemetry, live data feeds, event logs, quality data, maintenance history, and operational context to improve manufacturing prediction and closed-loop response Reconstruct equipment and process behavior from raw data and surface meaningful deviations between expected and actual execution Develop systems that identify process drift, classify fault patterns, and quantify operational risk before failures, downtime, or quality losses fully materialize Turn raw manufacturing signals into reliable services and applications that improve uptime, yield, and execution speed Develop Models That Matter Build and deploy machine learning models for anomaly detection, fault classification, process monitoring, quality prediction, forecasting, and related manufacturing use cases Develop models that connect recipe conditions, process parameters, equipment behavior, and intermediate process results to downstream product quality and performance outcomes Build feedforward and feedback models that use upstream signals, in-process data, and downstream results to improve decisions during execution Apply AI models and agentic workflows only where they materially improve engineering execution, diagnosis, knowledge retrieval, or workflow automation Build hybrid solutions that combine deterministic engineering logic, statistical me...