Rachith Dey-Prakash
Research Engineer · 3D Vision · Robotics · Deep Learning
Bio
I'm a Research Engineer passionate about building intelligent systems!
At Intel Labs, I've contributed to novel 3D object surface reconstruction methods, co-developed SPEAR (an open-source photorealistic simulator built on Unreal Engine 5), and led automation efforts that cut release times by over 95%. I've also driven evaluation pipelines for diffusion models to optimize for real-world deployment. I'm also actively involved in the academic community as part of the organizing committee for the Embodied AI Workshop at CVPR.
My background spans machine learning, computer vision, DevOps, and software engineering, with hands-on experience in C++, Python, PyTorch, Unreal Engine, and cloud infrastructures. I'm currently looking for opportunities to solve complex challenges and push the boundaries of AI-driven systems.
Updates
- Jun 2026Our paper on SPEAR was accepted to ECCV 2026! 🎉
- Jun 2026Part of the organizing committee for the Embodied-AI workshop at CVPR '26.
- Jun 2025Part of the organizing committee for the Embodied-AI workshop at CVPR '25.
- Jul 2024Generating synthetic data for 3D object surface reconstruction.
- Jun 2024SPEAR made its 5th open-source release! Check it out here.
- Oct 2023Presented SPEAR at the Intel Labs Open House event.
- Dec 2022SPEAR is now open-source! 🥳
- Oct 2020Building SPEAR — a simulator for photorealistic embodied AI research — from the ground up.
- Sep 2020Joined the Intelligent Systems Lab, led by Dr. Vladlen Koltun at Intel, as a research engineer.
Experience
-
Intel Labs
Research Engineer 2020 – 2025- SPEAR · open-source photorealistic simulator (Unreal Engine 5)
- 3D surface reconstruction · synthetic data · end-to-end model training
- Diffusion model evaluation pipelines · TIFA · HEIM
-
- Bayesian deep learning · reinforcement learning
- Graduate TA · ENPM662 Robot Modeling (Dr. Chad Kessens)
-
Nexteer Automotive
Perception Algorithm Intern May – Aug 2019- ADAS · threat assessment · polynomial trajectory planning · evasive maneuvers
- Road segmentation (FCN, KITTI)
- Simulation · algorithm design · on-road deployment
-
Micro Focus (formerly HP / Hewlett Packard Enterprise)
Software Engineer II 2016 – 2018- Operations Bridge Reporter (OBR) · AIOps, Monitoring Platform
- Vertica data warehousing · Vertica–OBR interoperability
- Docker/Kubernetes containerization · 50% smaller footprint
- Linux installation & config automation
-
Publications
-
M. Roberts, R. Wang, R. Zawar, R. Dey-Prakash, Q. Leboutet, S. Richter, M. Müller, G. Ros, R. Tang, S. Leutenegger, Y. Hold-Geoffroy, K. Sunkavalli, V. Koltun. “SPEAR: A Simulator for Photorealistic Embodied AI Research.” European Conference on Computer Vision (ECCV), 2026. (to appear)
Projects