Senior Machine Learning Engineer - VETi Platform

Kodiak Sciences
Palo Alto, CA, United States
3 months ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Artificial Intelligence Systems Engineering Computer Vision C++ (Programming Language) Program Optimization Cognitive Science Computer Programming Software Debugging Human-Computer Interaction Python (Programming Language) Machine Learning Tensorflow
+13 more
Smart Devices Software Engineering Graphics Processing Unit (GPU) Pytorch Transfer Learning Deep Learning Imager Information Technology Low Latency ONNX (Open Neural Network Exchange) Format Machine Learning Operations TensorRT Lidar

Job description

Our VETi - Visual Engagement Technology and Imager - platform is an AI-enabled wearable system combining advanced LiDAR, Optical Coherence Tomography (OCT), embedded computing, machine learning, and AR/VR technologies. VETi is being developed for applications in retina care, digital health, identity security, cognitive science, and broader AI-enabled vision technologies. We are looking for a Senior Machine Learning Engineer to build the AI foundation for Kodiak’s VETi platform, from model research and training to deployment on embedded medical imaging hardware. This role is well suited for an engineer with strong machine learning and software fundamentals who enjoys complex computer vision problems and is excited to ship AI that runs on real wearable devices.

Responsibilities

  • Lead the design, training, and deployment of machine learning models for wearable imaging and sensing systems - from research prototypes through production.
  • Develop computer vision models for image processing and analysis across multiple imaging modalities and sensors.
  • Analyze medical imaging data with deep learning models to support diagnostics and clinical decision-making.
  • Build training pipelines, data labeling workflows, and evaluation frameworks that scale across imaging datasets.
  • Integrate and optimize AI inference into the VETi platform’s real-time imaging and device-control stack, deploying to NPUs, GPUs, and embedded accelerators within latency, power, and memory budgets.
  • Debug model accuracy and performance across training, evaluation, and on-device environments.
  • Collaborate with electrical, optics, clinical, software, and systems engineering teams., This role is an opportunity to build AI for real-world physical systems-optics, sensors, and embedded computing-running on actual devices, not just in the cloud. You will work at the intersection of software, hardware, medical imaging, optics, AR/VR, LiDAR, OCT, and AI. The platform is novel, the technical challenges are significant, and the work has the potential to shape a new class of wearable vision technologies.

Requirements

Do you have experience in System deployment?, * B.S., M.S., or Ph.D. in AI, Computer Science, Electrical Engineering, Applied Mathematics, Physics, or a related technical discipline, or equivalent practical experience.

  • 5+ years of professional machine learning experience developing and deploying production models.
  • Strong programming experience in Python and C++, with at least one major ML framework (PyTorch, TensorFlow, or JAX) and solid software engineering practices.
  • Strong deep learning experience, particularly in computer vision (CNNs, transformers, segmentation, detection, classification).
  • Experience deploying models to edge devices, including model optimization (quantization, pruning, distillation) and inference runtimes (ONNX, TensorRT, or similar).
  • Ability to collaborate across machine learning, software, hardware, scientific, and engineering teams.

Additional Experience That Would Be Valuable

  • Experience with medical imaging data (OCT, fundus, retinal scans, MRI, CT, or similar).
  • Experience working with 3D or volumetric imaging data (e.g., OCT B-scans, volumetric MRI/CT).
  • Experience building AI agents for user interaction or human-in-the-loop systems.
  • Experience with self-supervised learning, transfer learning, or other data-efficient methods for limited labeled data.
  • Familiarity with regulated medical-device AI development (FDA SaMD, IEC 62304, ISO 13485), or willingness to learn.

About the company

Kodiak Sciences (Nasdaq: KOD) is advancing vision science by integrating retinal biology, optics, artificial intelligence, medical imaging, and next-generation wearable technologies.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:17 min

Validating lidar sensor models against real noise

Ulrich Wurstbauer +1 · LIVE

4:01 min

Live text-to-image generation and image editing implementation

Joerg Krall Joerg Krall · World Congress 2026 Europe

2:35 min

Preventing remote code execution in PyTorch models

Balázs Kiss · World Congress 2023

3:27 min

Applying machine learning to complex medical imaging processes

Karol Przystalski · LIVE

2:08 min

Processing physical environment data with lidar models

Oliver Zimmert · LIVE

2:15 min

Open-source community and machine learning frameworks

Gian Marco Iodice Gian Marco Iodice · World Congress 2025

Videos

See all

Related articles

See all