Senior Computer Vision Engineer

Obvio•San Carlos, CA

About The Position

Obvio deploys AI-assisted cameras to make streets safer. We’re hiring a Senior Computer Vision Engineer to build the models and ML systems behind reliable detection and tracking in real-world traffic environments. You will own the full model-development loop: data strategy, training, experimentation, evaluation, field validation, and continuous improvement. This is a hands-on individual-contributor role for someone who combines strong applied-ML judgment with the engineering discipline to make experiments reproducible, measurable, and fast.

Requirements

7+ years in machine learning or computer vision, with a track record of shipping and improving production models.
Deep hands-on experience with object detection and multi-object tracking, including modern architectures, data augmentation and evaluation methods.
Strong understanding of class imbalance, overfitting, dataset leakage, label noise, domain shift, model calibration, and statistically sound validation.
Experience building training infrastructure or platforms that support reproducible experiments, distributed training, hyperparameter search, metric comparison, and model lineage.
Strong Python and PyTorch skills, plus practical experience with large image/video datasets.
Experience validating models on deployed or field-collected data and owning the loop from failure discovery through retraining and verified improvement.
Demonstrated technical leadership across ambiguous, cross-functional work, with clear communication and strong ownership.

Nice To Haves

Experience with traffic, automotive, robotics, surveillance, or other video-analytics domains.
Experience with re-identification, trajectory modeling, occlusion handling, camera calibration, or multi-camera tracking.
Experience with active learning, weak supervision, synthetic data, automated labeling, or dataset-quality tooling.
Experience optimizing and deploying vision models on NVIDIA Jetson, Qualcomm Snapdragon, or other edge accelerators.

Responsibilities

Develop and improve object-detection and multi-object-tracking models for vehicles, pedestrians, and other road users across challenging real-world conditions.
Own data strategy for model quality: sampling, labeling, dataset versioning, hard-negative mining, class imbalance, edge cases, and feedback from deployed systems.
Design rigorous experiments and ablations; distinguish real improvements from overfitting, leakage, noisy labels, or gains that do not survive field deployment.
Build and evolve reproducible training pipelines with experiment tracking, configuration management, artifact lineage, model registries, metric dashboards, and automated hyperparameter search.
Define evaluation that reflects product behavior—not only aggregate metrics—including precision/recall trade-offs, class and scenario slices, calibration and tracking quality.
Partner with embedded engineers to optimize models for edge deployment while balancing accuracy, latency, memory & power constraints.
Set technical direction, lead design reviews, mentor engineers, and raise standards for ML rigor, reproducibility, and production readiness.