Senior Software Engineer, Spatial Intelligence and Foundation Models
$184k - $357k • Remote • US, CA, Santa Clara
Posted 1d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
Fully remote
Categories
LLM Engineer
About the job
NVIDIA is seeking a Software Engineer to join our Isaac Spatial Intelligence team, focusing on geometric and semantic understanding, and reasoning for robots. You will build perception systems that transform raw sensor data into actionable world understanding, contributing to the future of physical AI. This role involves designing, implementing, and deploying novel algorithms for spatial understanding, developing robust perception, mapping, and reasoning systems, and advancing the state of the art in geometric computer vision by combining classical multi-view geometry with deep learning. You will also train and evaluate vision-language models for robotics skills and collaborate with various teams to integrate and release applied research efforts.
Responsibilities
- Design, implement, and deploy novel algorithms for spatial understanding, including SLAM, structure-from-motion, optical flow, scene flow, and object reconstruction.
- Develop perception, mapping, and reasoning systems for robots, simulations, and large-scale data pipelines.
- Advance geometric computer vision by integrating multi-view geometry, optimization, and deep learning.
- Train and evaluate vision-language models on robotics-relevant skills.
- Collaborate with Cosmos, GR00T, and other Isaac teams on perception and spatial understanding for foundation models.
- Contribute to the integration, validation, and release of applied research on NVIDIA's robotics platforms.
- Foster innovation and collaboration, contributing to prototypes, open-source software, patents, and publications.
- Translate engineering work into impactful products by collaborating with product, hardware, and software teams.
Requirements
- PhD or Master's degree in Computer Science, Robotics, or a related field (or equivalent experience).
- 8+ years of experience in computer vision, robotics, or deep learning.
- Strong foundation in 3D geometric computer vision (multi-view geometry, visual odometry/SLAM, structure-from-motion, dense correspondence).
- Proficiency in Python and/or C++.
- Experience with Deep Learning frameworks (PyTorch, JAX, TensorFlow).
- Experience training and evaluating deep learning models for perception tasks.
- Familiarity with vision-language models is a strong plus.
- Strong skills in agentic tool use and AI coding agents/workflows (e.g., Claude Code, Cursor, Codex).
Benefits
- Equity
- Benefits