Lead Principal Applied Scientist - Robotics

Solution Identification and Strategy

Partner with science, engineering, product, and hardware leaders to identify strategic product needs where robotics, perception, and embodied AI can create measurable customer and business impact. Evaluate academic literature, industry benchmarks, robotics platforms, and commercially viable robot APIs to assess feasibility, technical difficulty, and delivery risks. Break down ambiguous robotics and AI problems into clear research plans, model architectures, data requirements, evaluation criteria, and production milestones. Set science quality standards for applied robotics workstreams, including perception accuracy, latency, robustness, safety, reliability, and operational feedback metrics. Prioritize solutions using the scientific process, including modeling approaches, evaluation techniques, data collection strategies, and risk/reward tradeoffs.

Applied Research and Model Development

• Lead the design and execution of research programs and POCs for sensors, multi-sensor fusion, real-time signal processing, and perception systems.
• Develop and guide approaches for object detection, tracking, activity recognition, scene understanding, and related perception capabilities in real-world environments.
• Advance multimodal AI systems that combine signals such as camera, depth, lidar, audio, telemetry, proprioception, and task context.
• Apply reinforcement learning, action-conditioned planning, decision-making, and reasoning methods to enable robot behaviors that are robust, measurable, and product-relevant.
• Define dataset strategy, data quality criteria, labeling approaches, simulation or synthetic data opportunities, and evaluation protocols for robotics and embodied AI use cases.
• Guide model training, fine-tuning, optimization, inference design, and compute/latency tradeoffs for real-time or near-real-time deployment scenarios.

Solution Delivery and Production Integration

• Lead full-stack execution across experimentation, data pipelines, model development, evaluation, deployment integration, and production monitoring.
• Partner closely with software engineering, machine learning engineering, hardware teams, and product stakeholders to integrate AI capabilities into robotic systems and services.
• Evaluate and review high-complexity code, establish best practices for repositories, version control, code review, documentation, testing, and delivery readiness.
• Define operational metrics and user feedback loops to assess delivered solutions in production and inform future technical strategy.
• Serve as an escalation point for complex robotics, AI, perception, and systems integration issues, driving root-cause analysis and durable solutions.

Research Leadership and Influence

• Demonstrate thought leadership in at least one business-critical area such as robot perception, multimodal systems, sensor fusion, reinforcement learning, or embodied AI.
• Translate research insights into clear technical recommendations, patents, white papers, design documents, demos, or conference-quality publications where appropriate.
• Mentor and guide scientists and engineers, raising the bar for applied research rigor, experimentation quality, and production readiness.
• Establish productive collaborations with internal teams, external research groups, academic partners, or commercial robotics ecosystem partners where relevant.

Core Competencies

• Bias for action with a strong hands-on orientation; able to move from ambiguous idea to prototype, evaluation, and production path quickly.
• Ability to execute full-stack AI workflows spanning data, experimentation, modeling, evaluation, APIs, deployment, and feedback loops.
• Strong cross-functional collaboration with hardware teams, software engineering, ML engineering, product, operations, and leadership stakeholders.
• Excellent judgment in balancing scientific rigor, product urgency, systems constraints, safety, reliability, and customer impact.
• Clear executive-level communication; able to explain complex robotics and AI tradeoffs to technical and non-technical audiences.

Required Technical Expertise

• Deep experience in machine learning, artificial intelligence, computer vision, perception, robotics, sensor fusion, real-time signal processing, or a closely related field.
• Experience with perception capabilities such as object detection, tracking, activity recognition, scene understanding, localization, or state estimation.
• Experience designing multimodal AI systems that combine heterogeneous data sources and reason over context, actions, and temporal signals.
• Practical knowledge of reinforcement learning, planning, sequential decision-making, robotics control interfaces, or action-conditioned model behavior.
• Strong programming capability in applicable languages such as Python and/or C++, and experience with modern ML frameworks and production-oriented software practices.
• Familiarity with APIs, SDKs, or integration patterns from commercially viable robotics platforms.