Senior Deep Learning Engineer, Cosmo 3D Spatial
At a glance
Senior Machine Learning Engineering role at NVIDIA. US, CA, Santa Clara · full-time · $224,000–$356,500 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Build spatial training data from real-world images and video, managing sourcing, filtering, curation and balanced coverage
- Create labeling workflows for 3D supervision, including camera-relative boxes, spatial questions, reference frames and cross-view matches
- Check data quality through deduplication, automated scoring and coverage reviews, then balance pre-training and fine-tuning datasets
- Run full training pipelines, track reproducibility and regressions, and trace capability changes to data or recipe decisions
- Develop spatial benchmarks and work with research scientists to test 3D hypotheses and guide model changes
What you bring
- At least twelve years building deep learning systems with Python and PyTorch or JAX on Linux
- An MS, PhD or equivalent experience in computer science, engineering, robotics or a related discipline
- Deep practical expertise in 3D vision, such as multi-view geometry, SLAM, camera pose or 3D reconstruction
- Experience creating vision-language training data and evaluations that improve visual grounding and reasoning
- A track record with large multimodal data pipelines and training models across multi-GPU, multi-node clusters
Who this fits
This senior engineering role suits someone who can turn 3D research questions into scalable data, training and evaluation work. You’ll partner with research scientists and operate large multi-node GPU clusters.
From the employer
NVIDIA is at the heart of the AI revolution, and Physical AI is its next frontier: machines that perceive, reason about, and act in the three-dimensional world. NVIDIA Cosmos is our open platform of world foundation models for Physical AI, built to interpret images, video, and text and turn them into a structured understanding of a physical scene: motion, object interactions, geometry, and physical context. These models are the reasoning layer for robots, autonomous vehicles, and smart infrastructure.
The Cosmos Engineering team builds the foundational capabilities behind these models. We are hiring a Senior Deep Learning Engineer to own the data engine and end-to-end training verification behind the 3D spatial reasoning and perception capabilities of these models: 2D and 3D grounding, metric geometry, spatial reference frames, cross-view correspondence, and embodied spatial reasoning. You will decide what the model learns geometry from, prove that it learned it, and work directly with research scientists in Cosmos Lab to turn 3D research hypotheses into measurable capability in shipped models. If you believe frontier model quality is won or lost in the data and the evaluations, this is the seat where that belief does the most work.
What you'll be doing:
Own the 3D data engine for Cosmos spatial reasoning: source, curate, filter, and balance large-scale real-world image and video corpora into vision-language training data with the coverage and diversity that spatial understanding demands.
Build the annotation and auto-labeling pipelines that produce 3D-grounded supervision at scale, camera-relative 3D boxes, referring and spatial question answering, free space and reachability, ego-, world-, and object-centric reference frames, cross-view correspondence, camera motion, distance and size, and chain-of-thought traces, validated by programmatic and model-based critics.
Own data quality end to end: semantic deduplication, automated quality scoring for faithfulness, completeness, and correctness, coverage analysis across scene types and reference frames, and the sampling strategies that keep pre-training and supervised fine-tuning mixtures balanced.
Verify end-to-end model training: run and validate full pre-training and supervised fine-tuning pipelines, guard reproducibility, catch data and checkpoint regressions, diagnose throughput and loss anomalies, and attribute capability changes back to the specific data and recipe decisions that caused them.
Build and operate the 3D and spatial evaluation suite, public benchmarks such as CV-Bench, BLINK, RefSpatial, VSI-Bench, SPAR-Bench, and RoboSpatial, NVIDIA's VANTAGE-Bench for real-world fixed-camera video understanding, and in-house benchmarks you design with continuous evaluation and full traceability from every reported score back to the exact weights, inputs, configuration, and evaluation code.
Partner closely with Cosmos Lab research scientists: translate 3D research hypotheses into dataset and ablation experiments, run them at scale, and feed honest results back into recipe and architecture decisions.
Operate on large multi-node GPU clusters, tuning data throughput, sharding, and dataloader performance so that data is never the bottleneck on a long training run.
Ship the results into Cosmos releases, open-source datasets and benchmarks where appropriate, and raise the bar for data and evaluation rigor across the team.
What we need to see:
MS or PhD in Computer Science, Electrical/Computer Engineering, Robotics, or a related field, or equivalent experience.
12+ years of proven experience building deep learning systems in Python with PyTorch or JAX on Linux.
Deep expertise in 3D computer vision, multi-view geometry, structure-from-motion or SLAM, depth and camera pose estimation, point cloud processing, or 3D reconstruction with the practical ability to produce and validate 3D ground truth at scale, not just consume it.
Hands-on experience with vision-language models, including building the training data and evaluations that measurably improve visual grounding and reasoning quality.
Demonstrated experience building large-scale multimodal data pipelines: distributed video and image processing, deduplication, captioning and annotation, automated quality metrics, and dataset versioning.
Experience running and validating large model training on multi-GPU, multi-node clusters, with working knowledge of distributed training and sharding strategies such as data, tensor, and pipeline parallelism or FSDP.
Rigorous evaluation methodology: designing benchmarks that resist gaming, building clean ablations, and reading results honestly enough to kill your own ideas.
Excellent written and verbal communication, with a track record of partnering effectively with research scientists and translating research direction into engineering execution.
Ways to stand out from the crowd:
PhD and/or publications at CVPR, ICCV, ECCV, NeurIPS, ICLR, or CoRL in 3D vision, multimodal learning, or embodied AI.
Experience curating web-scale or petabyte-scale video corpora, and building the distributed processing infrastructure behind it using Ray, Spark, Slurm, or similar.
Familiarity with 3D foundation models and modern auto-labeling techniques for geometry, camera estimation, and correspondence.
Experience with vision-language model post-training, supervised fine-tuning, chain-of-thought data design, reward modeling, or reinforcement learning with verifiable rewards applied to reasoning quality.
Experience building evaluation infrastructure and harnesses such as VLMEvalKit, including leaderboards, dashboards, and example-level failure inspection.
With competitive salaries and a generous benefits package, NVIDIA is widely considered to be one of the technology industry's most desirable employers. We have some of the most forward-thinking and versatile people in the world working with us, and our engineering teams are growing fast in some of the most impactful fields of our generation: Deep Learning, Artificial Intelligence, and Physical AI. If you're a creative engineer who enjoys autonomy and shares our passion for technology, we want to hear from you!
You will also be eligible for equity and benefits.
Applications for this job will be accepted at least until September 19, 2026.This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.
NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.