Back to jobs
Job Description
- Drive the design and maintenance of end-to-end ML deployment pipelines. Lead the team through model evaluation, fine-tuning, data processing, and debugging.
- Manage the critical trade-offs between model performance and hardware constraints (ARM SoCs, DSPs, NPUs). Be responsible for ensuring that ML-powered features respect device power consumption and latency budgets.
- Maintain high engineering standards for C++ development in an embedded context, ensuring scalable, and maintainable firmware and software architectures.