Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
Нижеразвернуть
$133к-190к/год
$190к$230кмедиана$260к
По похожим ролям (50) ~ $230к/год
На СНГ рынке: $4.2к/мес ($3.6к - $5к)
81
Крутая вакансия
развернуть
Чётко очерченная senior-роль в медицинской диагностике даёт серьёзную техническую ответственность и заметное влияние на продукт, но работа в офисе снижает гибкость.
Ниже рынка
Передовой AI-стек
Чёткая зона ответственности
Влияние на медицину
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Software AI Engineer 4 (AI): Designing, training, and validating deep learning models for cytology on the Genius Digital Diagnostics System with an accent on cell classification, nuclear-to-cytoplasmic ratio segmentation, and regulatory evidence. Focus on building multi-task computer vision models, preventing data leakage, validating model interpretability, and supporting FDA submissions under medical-device design controls.
Location: Marlborough, MA, United States; San Diego, CA, United States
Annualized base salary: $133,000–$190,000, plus bonus eligibility.
Company
hirify.global develops women’s health diagnostic and imaging solutions, including AI-enabled digital diagnostics.
What you will do
Design, train, tune, and validate multi-class CNN and multi-task deep learning models for cytology diagnostics.
Develop nucleus and cytoplasm segmentation networks to measure nuclear area and nuclear-to-cytoplasmic ratios, including overlapping cells.
Own data pipelines covering patient-grouped splits, color profiles, class balance, imaging metadata, leakage prevention, and reproducible experiment tracking.
Define metrics, benchmarks, evaluation reports, interpretability checks, and model verification and validation protocols.
Collaborate with cytopathologists on labeling, inter-observer agreement, and adjudication.
Prepare technical documentation for regulatory submissions, support AI medical-device strategy, and mentor engineers on coding, reproducibility, and MLOps standards.
Requirements
MS or PhD in computer science, biomedical engineering, electrical engineering, or a related field; alternatively, a BS with equivalent experience.
7+ years of software development experience, including 4+ years building and deploying deep learning models for computer vision.
Expert Python and PyTorch or TensorFlow skills, including CNN fine-tuning, transfer learning, and segmentation.
Experience with imbalanced, multi-class, and multi-task problems and metrics including per-class sensitivity, F1, kappa, and AUROC.
Experience with medical or microscopy imaging, including color handling, stain variation, and high-resolution tiling.
Strong data-splitting, leakage-prevention, experiment-tracking, and reproducible-training practices.
Clear written communication for technical reports and design documentation.
Nice to have
Digital pathology or cytology AI experience, ideally urine cytology.
Experience with FDA 510(k), De Novo, PMA, or EU IVDR submissions and familiarity with IEC 62304, ISO 13485, ISO 14971, 21 CFR Part 820, and FDA PCCP guidance.
ICC color management, stain deconvolution, scanner color calibration, and cell instance segmentation tools such as StarDist or Cellpose.
Annotation tools such as QuPath, CVAT, or napari.
Edge or embedded inference optimization using quantization, ONNX, or TensorRT.
Experience leading or technically guiding a small team; coaching and mentorship experience.
Culture & Benefits
Comprehensive onboarding training and continued professional development and training.
Bonus eligibility in addition to the annualized base salary.
Work supports AI-enabled medical devices and women’s health diagnostics.
Employment is subject to hirify.global’s standard equal-opportunity policy.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →