Senior Computer Vision & Machine Learning Engineer

illumicell AI is a medical-technology startup building AI-powered, label-free cell analysis to provide fast, objective diagnostics at the point of care. The startup is based at the Pagliuca Harvard Life Lab incubator in Allston and develops a digital holographic microscope for automated semen analysis. The product is a functional prototype device consisting of a digital holographic scanner paired with cloud-based AI analysis. illumicell AI is supported by Accel and Tim Draper, and is an alumni of Techstars.

• Experience developing and deploying computer vision or image-processing systems in production environments with responsibility beyond offline model development.
• Strong Python skills and hands-on production experience with PyTorch or comparable deep-learning frameworks.
• Sound experimental practices including dataset splitting, metric selection, ablation studies, reproducibility, and error analysis.
• Software engineering fundamentals: typed interfaces, unit and integration testing, version control, code review, and technical documentation.
• Ability to work from incompletely specified goals and scope incremental work.
• History of delivering complex technical projects through integration, review, and delivery.
• Comfortable using coding agents as engineering tools while maintaining accountability.
• Clear written and verbal communication in English (C1 level).
• MS or PhD in Computer Science, Electrical Engineering, Biomedical Engineering, or related field, or equivalent experience.

Nice to have:

• Experience with object detection for dense or small targets; familiarity with oriented bounding boxes, rotated detection, Detectron2, MMDetection.
• Knowledge of multi-object tracking methods including data association, Kalman filtering, Hungarian assignment, optical flow, track stitching, identity continuity, and appearance-based re-identification.
• Experience in medical imaging fields such as digital pathology, microscopy, cytology, or laboratory automation.
• Familiarity with ML infrastructure tools including experiment tracking (Weights & Biases, MLflow), model versioning, Docker training, cloud batch inference (GCP Batch, Vertex AI, AWS), and GPU profiling.
• Experience with regulated medical or safety-critical software standards such as IEC 62304, FDA SaMD, design controls, or analytical validation.
• Linux device software experience including camera or sensor acquisition, video handling, data upload, and inference on constrained hardware.
• Experience with OpenCV, NumPy, SciPy, ONNX, TensorRT, or CUDA performance analysis.
• Background in robotics, autonomous systems, video analytics, or quantitative measurement involving dense scenes and temporal consistency.
• Experience with Vision Transformers, self-supervised pretraining, or foundation models applied to scientific or medical images.
• Knowledge of statistical validation methods such as repeatability, reproducibility studies, method comparison, Bland-Altman analysis, sensitivity, and specificity estimation.
• Experience mentoring junior ML engineers.

• Take technical responsibility for computer vision capabilities from problem definition, benchmark design, development, integration, and quantitative evaluation.
• Develop, train, and deploy models for sperm detection, multi-object tracking, motility measurement, and image-quality assessment using PyTorch and production-grade frameworks.
• Design evaluation systems with subject-disjoint dataset splits, versioned models, clinically relevant metrics, and error analysis.
• Choose between classical image processing and deep learning approaches based on measured results.
• Define annotation requirements, labeling specifications, and ground-truth standards; collaborate with clinical and labeling partners.
• Perform GPU profiling, batch inference optimization, code review, testing, and deployment.
• Contribute to device acquisition software, device-to-cloud data handling, cloud batch workers, APIs, and integration testing as needed.
• Establish repeatable training workflows including versioned configurations, experiment tracking, and model provenance.
• Use coding agents and engineering automation critically for implementation, testing, investigation, documentation, and traceability.
• Review experiments and code from the ML team; provide technical review and mentorship.
• Investigate failures related to dense clusters, cell crossings, debris, drift, blur, and reconstruction artifacts.
• Work from incomplete specifications to produce reviewable and buildable results.

Please be informed that the data controller is Testasy Sp. z o.o. ("controller"). Candidates have rights regarding personal data including access, rectification, erasure, objection, portability, and complaint to supervisory authority. Data processing is for recruitment purposes; some data provision is mandatory under the Labour Code. Consent for additional data is voluntary and can be withdrawn at any time. Recipients include Just Join IT service and other entities involved in recruitment processing.