2 days ago
Remote, AmericasSenior
Base Salary
$200k - $260k/yr
Responsibilities
- Design the computer vision architecture for fine-grained item identification using foundation vision models adapted to the marketplace catalog.
- Build and productionize models for fine-grained product classification and set accuracy standards by category.
- Develop calibrated confidence scoring so the product can communicate model uncertainty.
- Partner with labeling providers to prioritize data collection and labeling based on model errors.
- Balance expanding category coverage with improving accuracy in existing categories.
- Own model development through production serving, including latency, cost, reliability, and low-latency APIs.
- Communicate model capabilities and limitations to technical and non-technical stakeholders.
Requirements
- At least 5 years of applied computer vision experience, including shipping production systems at meaningful scale.
- Hands-on experience with fine-grained or instance-level classification involving similar items.
- Production experience fine-tuning and deploying vision transformers or CNNs with PyTorch or TensorFlow.
- Experience building evaluation frameworks, calibrated confidence scoring, and model-serving systems with low-latency APIs.
- Experience adapting foundation vision models to specific use cases.
- Strong communication skills and comfort leading an open-ended technical problem.
Benefits
- Salary range of $200,000 to $260,000 USD annually.
- Remote within North America, including the United States.
Tech Stack
PyTorchTensorFlow