5+ years of applied computer vision experience with production systems at scale.
Hands-on expertise in fine-grained or instance-level recognition.
Proficient in fine-tuning and deploying vision transformers or CNNs using PyTorch or TensorFlow.
Experience adapting foundation vision models for specific catalogs.
Skilled in designing evaluation frameworks to measure model improvements.
Knowledge of calibrated confidence scoring and model serving decisions.
Strong communication skills for technical leadership.
Responsibilities
Design and own the computer vision architecture for catalog identification.
Define accuracy standards and develop confidence scoring for user communication.
Build feedback loops to prioritize labeling based on model errors.
Balance category coverage with accuracy in existing categories.
Oversee the transition from model research to production, focusing on latency and reliability.
Explain model capabilities and trade-offs to both technical and non-technical stakeholders.
Benefits
Hybrid work model based in New York, New York.
Full Job Description
About the Role
As the founding machine learning engineer, you will set the technical direction for fine-grained visual item identification at an internet marketplace platform. You will build production models that identify specific brands, models, editions, and variants, helping users make informed decisions with confidence. What You'll Do
Design and own computer vision architecture, adapting foundation vision models to specialized catalog identification.
Define category-level accuracy standards and develop calibrated confidence scoring so the product can communicate uncertainty.
Build feedback loops that use model errors to guide labeling priorities in partnership with the labeling team.
Balance broader category coverage against deeper accuracy in existing categories.
Own the path from model research to production serving, including latency, cost, and reliability.
Explain model capabilities and tradeoffs to technical and non-technical stakeholders.
What We're Looking For
At least 5 years of applied computer vision experience, including production systems delivered at meaningful scale.
Hands-on experience with fine-grained or instance-level recognition, distinguishing between visually similar items where near-misses are not sufficient.
Production experience fine-tuning and deploying vision transformers or CNNs with PyTorch or TensorFlow.
Experience adapting foundation vision models to specific use cases or catalogs.
Ability to design and run evaluation frameworks that measure model improvements beyond training loss.
Experience with calibrated confidence scoring and ownership of model serving decisions, including latency, cost, and reliability.
Strong written and verbal communication, and comfort providing technical leadership on an open-ended problem.
Compensation & Benefits
Base salary: $200,000 to $260,000 annually. Visa sponsorship is not available. Location
