Top Tech Jobs & Startup Jobs in San Francisco Bay Area, CA

Design and develop control systems for production robots, translating high-level motion commands into precise whole-body behavior. Implement hierarchical feedback loops, motor control software, compliant and force-sensitive controllers, and QP-based whole-body control. Develop embedded, real-time software integrated with custom hardware and communication interfaces. Build pipelines for sensing, encoder calibration, filtering, synchronization, and system characterization while ensuring robotic safety, timing, reliability, and robustness.

Develop and maintain real-time actuator and motor-control firmware for robotic systems from prototype through production. Design hierarchical feedback-control systems, architect reliable embedded software, validate motor controllers and sensors, and collaborate with electrical and mechanical engineers on custom hardware. Build calibration and sensing pipelines for encoders, current, voltage, filtering, synchronization, and system characterization while implementing safety mechanisms and meeting production timing and robustness requirements.

Design and develop the behavioral and autonomy architecture for real-world robots. Build systems that translate goals and robot state into coordinated actions, integrate perception, controls, navigation, and learned methods, and ensure safety through preconditions, fallbacks, timeouts, and recovery. Diagnose cross-stack issues involving latency, failures, and resource contention. Establish robust interfaces, review system-wide designs, and provide technical leadership across robotics teams.

Build and deploy vertically integrated robotic systems across hardware and software. Responsibilities include integrating sensors, troubleshooting cross-stack issues, bringing new robots from first power-on through deployment, configuring customer-specific workflows, validating robots at customer sites, and creating runbooks and tooling. The role requires hands-on experience with robotic or electromechanical systems, hardware and software debugging, and deployment or integration at customer locations.

Build and own the robotics simulation platform, including environments, robot models, actuator and contact modeling, GPU-parallel training infrastructure, system identification, domain randomization, regression testing, and CAD-to-simulation asset pipelines. The role focuses on improving simulation fidelity, performance, reproducibility, and sim-to-real transfer for controls, planning, SLAM, and manipulation systems.

Design and ship end-to-end teleoperation systems for bimanual home robots. Build VR and 3D operator interfaces, integrate headsets and controllers, develop motion-retargeting and optimization-based control, reduce perceived network latency, and create shared-autonomy capabilities. Specify ergonomic operator stations and collaborate across mechanical, robotics, and software teams. The role combines HCI, sensing, ergonomics, robotics, systems profiling, and empirical testing to deliver reliable tools used by operators in real-world settings.

Conduct independent robot-learning research from hypothesis through data, model training, deployment, and evaluation. Establish long-term research direction, experiment with novel architectures and post-training methods, develop data strategies, deploy models on physical robots, define real-world metrics, and build scalable machine-learning infrastructure for research and production.

Design and develop robotic actuators, including transmissions, motor integration, structural packages, bearings, sealing, and thermal systems. Define and run life testing using fleet-derived load spectra, perform teardown analysis, and establish evidence-based design margins. Collaborate on in-house assembly, calibration, end-of-line testing, and actuator performance roadmaps. The role requires precision mechanical design, geartrain analysis, manufacturing and DFM expertise, CAD, FEA, tolerance analysis, GD&T, fatigue, and thermal design experience.

Architect and build terabyte-scale robotics data pipelines from fleet sensor streams through training ingestion. Curate, preprocess, annotate, version, and validate datasets; analyze data coverage, drift, redundancy, and quality; mine scenarios using embeddings and models; and develop samplers, benchmarks, and evaluation datasets. Partner with ML researchers to diagnose model failures and create targeted data mixtures and processing workflows that improve robot-learning performance.

Build and optimize end-to-end machine learning training infrastructure for large-scale multimodal robot data. Responsibilities include distributed training, data ingestion and transformation, checkpointing, orchestration, experiment tracking, sampling and curation, performance profiling, debugging data and training issues, and converting research prototypes into production infrastructure. The role may also involve robot learning, cloud and cluster infrastructure, post-training, on-robot inference optimization, CUDA or Triton kernels, and video-heavy datasets.