Senior Software Engineer, Dermatology Inference

Tono Health•Brooklyn, NY
•$180,000 - $325,000•Hybrid

About The Position

Tono builds software and operations to make specialty care faster to access and easier to deliver, starting with dermatology. The company operates its own clinics, including a national telehealth practice and an in-person clinic in DUMBO, Brooklyn, and is building an autonomous electronic health record for specialty clinics. The Senior Software Engineer, Dermatology Inference will develop specialized models that help dermatologists see more, identify changes earlier, and make decisions faster. The role owns the path from research through production, including model development, training, evaluation, deployment, and integration into clinicians’ workflows. The engineer will collaborate closely with physicians, co-founders, and product engineers in a regulated care environment, with emphasis on patient safety, reliability, maintainability, and responsible model performance.

Requirements

  • At least 5 years of software engineering experience, including training and shipping machine-learning or computer-vision models into production.
  • Strong Python and deep-learning experience, such as PyTorch or similar.
  • Hands-on computer-vision experience in areas such as classification, detection, segmentation, or image registration.
  • Experience with fine-tuning and adaptation methods such as LoRA or transfer learning for vision or multimodal models.
  • A rigorous approach to evaluation, including clinically meaningful metrics, calibration, held-out and external validation sets, and awareness of bias and failure across skin tones and imaging conditions.
  • Experience building and serving production models, including GPU workloads, inference performance, cost, and monitoring.
  • Experience building datasets and labeling workflows with domain experts.
  • Comfort with relational databases, data pipelines, and iterative delivery using feature flags and instrumentation.
  • Comfort working in a TypeScript product codebase or eagerness to learn it.
  • Care for patient safety, privacy, and reliability, and pride in the quality of one’s work.

Nice To Haves

  • Dermatology or medical-imaging experience.
  • Experience with longitudinal or change-detection models.
  • Published research or open-source work in computer vision.
  • Experience in regulated environments, including HIPAA or FDA Software as a Medical Device (SaMD).
  • Startup experience.
  • Experience working directly with clinicians.

Responsibilities

  • Develop, train, evaluate, and deploy dermatology models, including image-based diagnostic support and longitudinal lesion detection and tracking.
  • Train and fine-tune vision and multimodal models, using methods such as LoRA and other adaptation approaches; determine when to build custom models versus adapt open-source models.
  • Build pipelines to align and compare lesion images across visits, accounting for differences in lighting, angle, camera, and skin tone.
  • Create labeled datasets and clinician-supported annotation workflows, and use them for rigorous model evaluation.
  • Build and operate inference services, including model serving, batching, latency, and cost optimization.
  • Add confidence scoring, uncertainty estimation, and human-in-the-loop review to support trustworthy clinical use.
  • Monitor production models for drift, image quality issues, and failure cases, including performance analysis across skin tones and patient groups.
  • Integrate model outputs into the TypeScript product and clinicians’ workflows.
  • Ship safely in a regulated environment using careful reviews, feature flags, and safe rollouts.
  • Contribute across frontend, backend, data, and infrastructure as needed; maintain observability and improve system maintainability and performance.

Benefits

  • Meaningful equity in a high-growth, venture-backed company.
  • Medical, dental, and vision coverage.
  • Direct access to founders and an agile team with visible impact.
  • Weekly demos with leadership.
  • Unlimited paid time off.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service