Software Engineer Jobs in Santa Clara, CA

Build and maintain a calibration pipeline for multi-sensor vehicles, manage calibration lifecycle and deployment, support offline and online calibration algorithms, enable sensor fusion across cameras, lidar, radar and inertial sensors, collaborate with algorithm teams, and integrate calibration status into HMI for production workflows.

Develop, prototype, evaluate, and deploy ML-first behavior prediction and planning models to forecast motion and interactions of road users. Build software and infrastructure for behavior-specific ML, collaborate with perception and planning teams, and productionize models for autonomy systems.

Design, develop, and test backend and tooling for autonomy simulation products. Build features, integrate ML Sim Agent into closed-loop evaluation pipelines, optimize cloud compute/storage, and collaborate with infrastructure, robotics, and graphics teams to deliver scalable autonomy development tools.

Develop high-performance motion planning modules for onroad autonomous vehicles, integrating lightweight maps and perception outputs. Ship production C++ code, deploy to vehicle hardware, test on road, and collaborate with customers to meet diverse operational design domains.

Develop core middleware components for an SDV platform using C++; implement high-performance communication services (SOME/IP, DDS, Protobuf/gRPC), work on AUTOSAR Adaptive clusters, optimize multithreading and networking on Ethernet, and design system management (health, diagnostics) for safety-critical distributed vehicle systems.

Design and implement onboard application software in modern C++, collaborate with cross-functional teams to align interfaces and execution models across the autonomy stack, and contribute to building autonomy systems for on-road and off-road vehicles.

Design and implement low-speed motion planning and control modules for autonomous vehicles, characterize vehicle dynamics to close sim-to-real gaps, evaluate academic research, and build optimal-control solutions (e.g., nonlinear MPC, MPPI) deployable on production vehicle platforms.

Build and maintain large-scale ETL and ML infrastructure to automate data selection, labeling, training, and testing loops. Connect real-world and simulation data to enable continuous model improvement, collaborate with modeling teams, and mentor junior engineers to scale data-centric development.

Design and implement lifelong mapping and localization systems for vehicles, build scalable local/global maps, fuse live sensor data with maps, develop real-time onboard and offboard localization, leverage inertial/GNSS/camera/lidar/radar data, and continuously improve performance using large-scale, data-driven methods.

Lead development and optimization of neural rendering systems (e.g., 3D Gaussian splatting, NeRFs) for real-time simulation. Design CUDA GPU pipelines and multi-threaded C++ systems, integrate neural and classical rendering, prototype research, productionize techniques, and build tooling for profiling and CI-based performance regression tracking.

Build and operate the Insights data and analytics platform: ingestion, reliability, query infrastructure, visualization, dataset lifecycle, governance, transformation, and agentic analytics for physical AI at scale.

Design and implement scalable, secure Over-the-Air update platforms in C++ and Go. Build cloud-native infrastructure, package management, CDNs/PDNs, secure delivery pipelines (cryptographic signing, encrypted channels), containerized deployment, monitoring and analytics, and support large-scale device fleets across embedded Linux and RTOS devices.

Build scalable telematics backend systems and data pipelines to ingest, process, and analyze high-volume real-time telemetry from millions of devices. Design microservices, cloud storage, D2D communication, and integrate analytics/ML for predictive maintenance and fleet insights. Collaborate cross-functionally to deliver production-grade, high-availability telematics solutions.

Build and maintain large-scale cloud simulation infrastructure across AWS, GCP, and Azure. Improve deployment reliability, monitor and resolve bottlenecks, optimize CI/CD and developer tooling, and ensure interoperability with customers' autonomy software.

Build and productionize scalable backend services, APIs, and AI workflows to connect requirements, modeling, validation, and test data for autonomous vehicle programs. Implement traceability, versioning, dashboards, and KPIs, refactor prototypes into certifiable systems, and collaborate with systems engineering, safety, and autonomy teams to support compliance and validation at scale.

Build tools and infrastructure to enable large-scale end-to-end autonomy research and productionize self-driving software. Scale training, manage large datasets, identify and remove bottlenecks across GPU compute, data curation, and evaluation systems while collaborating with AI research and engineering teams.

Own and maintain HD maps infrastructure across products. Define map storage formats, distribute map data for UIs, data pipelines, storage, and SDKs. Collaborate with engineers and customers to design and build mapping and localization features for autonomous vehicle and simulation applications.

Build scalable Python-based tooling and infrastructure for autonomous vehicles, including systems for fleet management and vehicle communication. Design systems supporting multiple vehicle platforms and environments, collaborate across the autonomy stack, and support development, testing, and deployment of autonomy software.

Build and ship shared AI infrastructure, agent frameworks, and tooling; partner with product teams to productionize LLM and agentic features; own GenAI best practices for architecture, safety, evaluation, and deployment; develop agentic systems and AI SRE tooling; engage with customers to shape roadmap and demos.

Design, implement, and evaluate perception algorithms and 4D world representations for autonomous vehicles. Train and deploy ML and computer vision models from data collection to production, test on real vehicles, and collaborate with data, behavior, and research teams to deliver production-ready autonomy software.

Design, implement, and tune locomotion, whole-body control, and manipulation software for bi-dexterous robots. Integrate subsystems across actuators, sensors, and motor controllers, develop real-time C++ control, validate in simulation, debug hardware failures, and contribute to fleet tooling and CI/CD pipelines.

Design and ship deterministic, safety-critical classical or ML motion planners for fallback and minimal-risk maneuvers. Build planners for degraded perception and partial observability, evaluate behavior at scale using simulation and real-world data, develop metrics and analysis tools, and collaborate with perception, prediction, controls, safety, and remote assistance teams to deliver a reusable fallback platform.

Design, build, and maintain scalable, low-latency backend services and cloud infrastructure for remote assistance. Implement APIs, data pipelines, protobuf/gRPC communication, NoSQL persistence (Redis), real-time data streaming, and resilience across AWS regions. Collaborate with onboard and frontend teams to ensure secure, reliable end-to-end data flow and optimize serialization and transmission.

Develop and maintain full-stack applications supporting foundation-model research. Design client- and server-side architecture, ensure responsiveness, security, and performance, collaborate with researchers/ML engineers, troubleshoot and document software, and contribute to HPC and deep-learning research outputs and publications.

Entry-level software engineer working on data storage and management. Contribute across the SDLC to improve data efficiency, performance, scalability, and replication. Collaborate with senior engineers, write high-quality C++ code, and support automated testing in an in-office Santa Clara environment.