Software Engineer - Sensing, Consumer Products
About The Position
As a Software Engineer on Consumer Products Research, you’ll sit at the boundary between algorithm development and shippable systems. You’ll work closely with algorithm engineers to translate prototypes into clean interfaces, reliable pipelines, and efficient on-device implementations—with strong attention to performance, observability, and real-world failure modes. This is a software role first: we’re looking for someone who loves writing great code every day, takes pride in engineering craft, and is comfortable going deep enough into the algorithmic details to make the system work end-to-end. This role is based in San Francisco, CA. We use a hybrid work model of four days in the office per week and offer relocation assistance to new employees.
Requirements
- Love writing great software and want your work to sit close to novel sensing and edge algorithms.
- Understand algorithm behavior well enough to integrate, debug, and evaluate it—even if you’re not the primary model inventor.
- Have shipped production Python systems and care about clean interfaces, tests, and long-term maintainability.
- Enjoy embedded/on-device work and can debug across hardware, firmware, and higher-level application layers.
- Care about performance engineering and know how to profile and optimize under tight device constraints.
- Take ownership end-to-end and thrive in ambiguous, fast-moving, zero-to-one environments.
Nice To Haves
- Zephyr (or similar RTOS) experience.
- On-device ML deployment (NPU/GPU/DSP) and accelerator-aware profiling/optimization.
- Background in multimodal sensing, sensor fusion, or on-device perception.
- Experience building data collection systems and human-in-the-loop workflows (protocols, QA, metadata)
Responsibilities
- Build and ship production software for sensing algorithms, translating algorithm prototypes into reliable end-to-end systems.
- Implement and own key parts of the Python shipping pipeline (integration surfaces, evaluation hooks, and quality/performance guardrails).
- Develop embedded/on-device software in an RTOS environment (e.g., Zephyr) and deploy models to device runtimes and hardware accelerators.
- Optimize real-time on-device perception loops (e.g., detection/tracking-style pipelines) for stability, latency, power, and memory constraints.
- Create data collection + instrumentation tooling to bring up new sensing modalities and accelerate iteration from prototype → dataset → model → device.
- Partner cross-functionally (algorithms, human data, firmware/hardware) to debug, profile, and harden systems against real-world variability.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
Number of Employees
1,001-5,000 employees
