Robot Learning Research Intern

Bosch Group•Pittsburgh, PA

About The Position

The Robot Learning Lab at the Bosch Center for Artificial Intelligence in Pittsburgh seeks research interns to develop robots that learn transferable skills, adapt to unfamiliar situations, and improve through real-world experience. The lab works across robot learning, multimodal machine learning, embodied AI, and generative AI, combining industrial research with collaborations at Carnegie Mellon University's Robotics Institute. Research areas include robot foundation models; agentic robot systems; dexterous and contact-rich manipulation; transferable robot skills; and simulation and world modeling. Interns help formulate research questions, develop methods, and evaluate systems in simulation and on physical robots, with the goal of publishing at leading robotics and machine learning venues and translating scientific insights into practical robotic capabilities. Interns work closely with mentors and collaborators to own an ambitious research project. They review prior work, formulate hypotheses, plan and implement research, and conduct rigorous experiments. Projects may involve multimodal representations and transferable policies, imitation or reinforcement learning, robot foundation models, adaptation and failure recovery at deployment, data and simulation pipelines, or reliable implementation and evaluation. Interns collaborate on research publications and may contribute to invention disclosures and patent applications.

Requirements

  • Currently pursuing a Ph.D. or a recent postdoctoral researcher in Robotics, Machine Learning, Computer Science, Computer Engineering, Electrical Engineering, or a closely related field.
  • Minimum GPA of 3.0 on a 4.0 scale, or equivalent.
  • Strong foundations in machine learning and robot learning, including representation learning, policy learning, optimization, and experimental design.
  • Hands-on experience training or adapting modern robot policies and foundation models, such as vision-language-action transformers, diffusion or flow-matching action heads, or world action models.
  • Relevant training experience with multi-task pretraining, behavior cloning or supervised fine-tuning objectives, or offline or online reinforcement-learning post-training using actor-critic or policy-gradient methods.
  • Strong Python skills and experience implementing, debugging, and evaluating neural models using PyTorch or a comparable framework.
  • Hands-on experience using coding agents to develop, test, and maintain robotics and machine-learning software, including reviewing and validating agent-generated code.
  • Practical experience with physical robot platforms, including robot data collection, policy deployment, and closed-loop experimentation.
  • Ability to design rigorous evaluations using appropriate baselines, ablations, and diagnostic analyses to characterize generalization, robustness, and failure modes.
  • Demonstrated research ownership, supported by publications, preprints, or substantial research projects, along with clear technical communication and effective collaboration.

Nice To Haves

  • Experience training or adapting robot foundation models using heterogeneous human demonstrations, robot trajectories, and synthetic data, including data curation, quality assessment, and cross-embodiment transfer.
  • Experience integrating large language models, vision-language models, or other multimodal foundation models into robot perception, planning, control, or evaluation workflows.
  • Experience with test-time adaptation, policy steering, embodied memory, failure detection and recovery, or agentic systems that generate, execute, and refine robot skills.
  • Experience in dexterous or contact-rich manipulation, including learning from visual, tactile, force, proprioceptive, or acoustic feedback.
  • Experience with simulation, generative world models, digital twins, or Real2Sim2Real pipelines for policy training, evaluation, and transfer.
  • Experience with multi-GPU or multi-node training, efficient fine-tuning and inference, and reproducible workflows using versioned datasets, experiment tracking, and checkpoint management.
  • Proficiency developing robotics and machine-learning software on Linux using version control and maintainable software practices.
  • Theoretical depth in transfer learning, reinforcement learning, optimization, uncertainty estimation, or safe learning and control.
  • A strong publication record at leading robotics, machine-learning, or computer-vision venues, particularly with methodological depth and careful empirical validation.

Responsibilities

  • Define a focused research problem with mentors and collaborators, connecting a scientific question to a robotics or automation challenge.
  • Review relevant literature, identify limitations in existing approaches, and articulate a testable research hypothesis.
  • Develop an R&D plan covering methods, data sources, experimental settings, evaluation metrics, milestones, and target publication venues.
  • Design and implement proposed approaches, maintaining reproducible code, documented experimental configurations, and clear records of results.
  • Evaluate methods in simulation and on physical robots using quantitative comparisons, targeted ablations, qualitative analysis, and theoretical analysis where appropriate.
  • Share progress, literature, findings, and open challenges in weekly discussions, and refine the research plan as evidence emerges.
  • Prepare research manuscripts with collaborators for submission to leading venues, and contribute to related technical reports and patent materials.
  • Collaborate on research contributions for publication and invention disclosures or patent applications arising from the work.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service