Clera The Founding Machine Learning Engineer at Clera designs and owns computer vision architecture for fine-grained item identification. This role builds production models and manages the full lifecycle from research to production serving.
Responsibilities
As the founding computer vision engineer at an early-stage internet marketplace, you will set the technical direction for identifying and valuing items from images. You will build production models that distinguish closely related items and communicate uncertainty clearly, helping users make decisions with confidence.
Design and own computer vision architecture for fine-grained identification, adapting foundation vision models to a specific catalog.
Define accuracy standards by category and build calibrated confidence scores so the product can express uncertainty rather than guess.
Work with labeling partners to turn model errors into priorities for future data collection.
Balance expansion into new categories with improving accuracy in existing ones.
Own the path from model research to production serving, including latency, cost, and reliability.
Explain the model's capabilities and limitations to technical and non-technical stakeholders.
Qualification
Experience with active learning
Required
At least 5 years of applied computer vision experience, including production systems shipped at meaningful scale.
Industry experience with image or item identification, object recognition, or detection, including fine-grained or instance-level classification where similar items must be distinguished accurately.
Hands-on production experience fine-tuning and deploying vision transformers or CNNs with 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 with active learning, human-in-the-loop labeling, visual search, marketplaces, or an early-stage startup is a plus.
Preferred
Experience with active learning, human-in-the-loop labeling, visual search, marketplaces, or early-stage startups
