Join an early-stage marketplace company as its first machine learning engineer focused on computer vision. You will lead the design and production deployment of fine-grained item identification models, helping users identify products accurately and reliably from photos.
Design computer vision architecture for identifying items by brand, model, edition, and variant, adapting foundation vision models to a specific catalog.
Define category-level accuracy standards and build calibrated confidence scoring so the product can communicate uncertainty appropriately.
Create feedback loops that use model errors to guide labeling priorities in partnership with the labeling team.
Set priorities between expanding category coverage and improving accuracy in existing categories.
Own the model serving path from research through production, balancing latency, cost, and reliability at scale.
Explain model capabilities, limitations, and technical tradeoffs to company stakeholders.
At least 5 years of applied computer vision experience, including shipping systems to production at meaningful scale.
Hands-on experience with fine-grained or instance-level recognition, distinguishing visually similar products where near-misses are not acceptable.
Production experience fine-tuning and deploying vision transformers or CNNs using PyTorch or TensorFlow.
Experience adapting foundation vision models to specific use cases, and designing evaluation frameworks that measure progress beyond loss metrics.
Experience with calibrated prediction confidence and ownership of model serving decisions, including latency, cost, and reliability.
Clear written and verbal communication skills, and comfort leading technical direction on an open-ended problem. Active learning, human-in-the-loop labeling, low-latency APIs, and early-stage startup experience are useful.
Base salary: $200,000 to $260,000 annually. Visa sponsorship is not available.
Hybrid role based in New York, New York.