Founding Machine Learning Engineer, Computer Vision (Object Detection)
Job Description
The founding Machine Learning Engineer for Computer Vision at Clera will set the technical direction for extracting item identity and value from images. This role focuses on building production-ready fine-grained object detection systems with calibrated uncertainty and end-to-end serving.
Role Overview
As the founding computer vision engineer at an early-stage internet marketplace, you will lead technical decisions for identifying and valuing items from images. The work includes designing models that distinguish closely related items and clearly communicate uncertainty so users can make decisions with confidence.
Key Responsibilities
- Design and own the computer vision architecture for fine-grained identification, adapting foundation vision models to a specific catalog.
- Define accuracy standards by category and implement calibrated confidence scores so the product reflects uncertainty instead of relying on guesses.
- Partner with labeling collaborators to convert model errors into clear priorities for future data collection.
- Manage trade-offs between expanding into new categories and improving accuracy across existing ones.
- Own the full path from model research to production serving, covering latency, cost, and reliability.
- Communicate model capabilities and limitations to both technical and non-technical stakeholders.
Required Qualifications
- At least 5 years of applied computer vision experience, including production systems shipped at meaningful scale.
- Industry experience in image or item identification, object recognition, or detection, including fine-grained or instance-level classification where similar items must be distinguished accurately.
- Hands-on experience fine-tuning and deploying vision transformers or CNNs using PyTorch or TensorFlow.
- Experience adapting foundation vision models, building evaluation frameworks beyond loss metrics, and developing calibrated confidence scoring.
- Experience owning production model serving decisions, including latency, cost, and reliability; familiarity with low-latency APIs is useful.
- Strong communication skills and the ability to lead technical decisions on an open-ended problem.
- Experience in active learning, human-in-the-loop labeling, visual search, marketplaces, or an early-stage startup is a plus.
Technologies
- PyTorch
- TensorFlow
- Vision transformers
- CNNs
Compensation & Benefits
- Base salary: USD 200,000 to 260,000 per year.
- Visa sponsorship: Not available.
Location
Hybrid in New York, New York, United States.