Tech Lead, Robotics Runtime & Middleware
Mind Robotics17 hours ago
Palo Alto, CA, USAStaff+
Responsibilities
- Design and build the robotics runtime and middleware layer, including topic and message architecture, QoS policies, and multiprocess communication under tight latency budgets.
- Own the inference-serving path for onboard VLA and action-expert models, including batching, quantization, hardware acceleration, and accuracy versus control-loop latency tradeoffs.
- Architect multisensor synchronization and fusion across different clocks and cadences for coherent closed-loop control.
- Make technical decisions about middleware, process and thread architecture, and real-time guarantees.
- Set technical standards and conduct deep design and code reviews across runtime engineering.
- Prototype and de-risk new middleware, compute hardware, and model-serving architectures.
- Collaborate directly with modeling and research teams to translate policy requirements into runtime architecture.
- Provide technical mentorship or informal lead direction without formal management responsibility.
Requirements
- Strong systems programming experience in Python and/or Rust.
- Hands-on robotics middleware experience with ROS2, including custom message types, QoS tuning, and multinode communication patterns.
- Experience with ROS2 components such as rclcpp, rclpy, DDS implementations including Fast DDS and CycloneDDS, or Zenoh.
- Understanding of real-time scheduling, latency budgets, jitter, soft and hard real-time guarantees, and RTOS concepts.
- Experience with embedded or edge Linux, cross-compilation, device driver basics, and resource-constrained execution.
- Experience with time synchronization protocols such as PTP and gPTP, sensor fusion pipelines, and clock drift or skew across distributed compute.
- Experience deploying and optimizing models with ONNX Runtime, TensorRT, or similar technologies, including quantization and batching for edge inference.
- Experience with control systems and motion primitives, including the effects of message latency, action chunking, and control frequency on robot behavior.
- Track record of taking real-time systems from prototype to reliable continuous operation on physical hardware.
- Strong technical judgment regarding research velocity, runtime reliability, determinism, fault tolerance, and safety margins.
- Ability to make build-versus-buy decisions for middleware and compute hardware.
- Clear communication and ability to work directly with research and modeling partners.
About Mind Robotics
Mind Robotics builds generalizable industrial robots and the software runtime that lets them perceive, decide, and act under hard real-time constraints. It sells robotic systems and AI-driven middleware for factory-floor tasks, working directly with manufacturers; it has publicly cited a deployment partnership with Rivian. Founded in 2025 and headquartered in Palo Alto, the privately held company focuses on dexterous, adaptive automation for complex production environments.