Summary
Shivam Goel is a robotics researcher and PhD candidate at Tufts' MULIP Lab with a decade of experience building data-efficient, adaptive reinforcement learning systems that transfer from simulation to real robots. He designs neurosymbolic and hybrid learning pipelines that integrate learned policies with task-and-motion planning, force sensing, and classical robotics priors to enable robust on-the-fly adaptation under novelty and uncertainty. His work spans grid-world abstractions to large-scale simulators (MuJoCo, Isaac Sim) and real-world deployment via ROS/ROS2, emphasizing reproducibility and engineering-ready solutions. Shivam has led end-to-end systems validated on physical hardware with publications in AIJ, ICRA, and AAMAS, and focuses on reducing data needs through structured inductive biases. He is pragmatic about impact: methods must scale and work reliably on real robots to be considered complete. Based in Boston, he seeks research roles that blend close engineering collaboration with measurable real-world outcomes.
10 years of coding experience
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Tufts University
High School, High School at Methodist High School
Master of Science (M.S.) Computer Science, Master of Science (M.S.) Computer Science at Washington State University
Bachelor of Technology (B.Tech.) Information Technology, Bachelor of Technology (B.Tech.) Information Technology at Dr. A.P.J. Abdul Kalam Technical University
English, Hindi