Research Scientist - Cyber-Physical AI & Reasoning

Bosch Group•Pittsburgh, PA

12d

About The Position

The Cyber-Physical AI and Reasoning group at Bosch Research Pittsburgh develops intelligent systems that tightly integrate learning, reasoning, perception, and physical interaction. Our mission is to build safe, robust, and adaptive cyber-physical systems that operate reliably in real-world environments—spanning robotics, automation, manufacturing, and intelligent devices. We focus on systems that combine data-driven learning with structured models, physical constraints, and embedded intelligence, enabling machines to sense, decide, and act across diverse scenarios while continuously improving over time, including through interaction with humans. Core Research & Development Areas Our work spans a broad range of Cyber-Physical AI topics, including but not limited to: Embodied and Cyber-Physical AI Robot learning and control in physical environments Dexterous manipulation and automation for manufacturing Human–machine interaction and shared autonomy Hybrid and Model-Based AI Combining learning-based models with physics-based, symbolic, or optimization-based components World models, state estimation, and system identification Safety-aware and constraint-driven learning and control Multimodal & Foundation Models Vision-Language(-Action) models for perception, planning, and control Representation learning across modalities (vision, language, proprioception, signals) Cross-domain and cross-embodiment generalization Cyber-Physical Systems & Embedded Intelligence Embedded ML and edge AI for real-time systems Integration of learning algorithms with sensors, actuators, and control stacks Sim-to-real transfer and deployment on physical platforms Engineering & Prototyping System prototyping Data collection pipelines, simulation environments, and benchmarking frameworks Deployment of AI systems to industrial settings

Requirements

Master’s or Ph.D. in Computer Science, Robotics, Electrical/Mechanical Engineering, Machine Learning, or a related field
Strong foundation in AI/ML, cyber-physical systems, robotics, control
Experience with programming and experimental system development
State estimation, system modeling, or dynamics
Safety, robustness, or generalization in physical systems
Robot perception, control, planning, or manipulation
Embedded systems, real-time systems, or edge AI
Integration of ML models with hardware, sensors, and control software
Experience with simulation tools, robotics middleware, or control stacks
Multimodal learning, representation learning, or foundation models
Reinforcement learning, imitation learning, or optimal control
Hybrid approaches combining data-driven and model-based methods (e.g., neuro-symbolic integration)
Training and evaluating neural models (single- or multi-GPU)
Data curation, dataset analysis, and benchmarking
Debugging non-convex optimization and real-world system failures

Nice To Haves

Experience with physical or robotic hardware systems
Experience with embedded or real-time systems
Experience with multimodal foundation models
Exposure to hybrid or model-based AI methods
Prior research publications, technical reports, or strong project portfolios
Experience collaborating in interdisciplinary or industrial research teams

Responsibilities

Defining and investigating compelling problems in Cyber-Physical AI & Reasoning
Designing, implementing, and evaluating learning-based or hybrid AI systems
Conducting literature reviews and translating insights into practical system designs
Developing experimental pipelines (simulation, real-world testing, data collection)
Analyzing system performance, robustness, safety, and failure modes
Collaborating with interdisciplinary teams spanning AI, robotics, and engineering
Research publications and technical reports
Industrial patents and technology transfer
Prototypes deployed in labs or production environments

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume