Job description

The company Norbert is building autonomous robots that deliver healthcare. Our AI sensing platform mounts on mobile robots and does the work of a care team member—rounding on patients, capturing vitals without contact (FDA-cleared for pulse and respiratory rate, more in the pipeline), running assessments, documenting to the EMR, and escalating when something's wrong. Autonomously. We're not building demos. We're deployed in real facilities today, monitoring hundreds of patients daily. We're solving one of healthcare's hardest problems: a global nursing shortage that will hit 40% by 2030. We're a small, international team backed by top-tier VCs, with offices in Brooklyn and Paris. We ship things that matter. The position We are looking for our lead deep learning engineer to spearhead the development of our groundbreaking sensing technology. What you will do: • Design, fine-tune, and deploy computer vision models (YOLO, InsightFace, MediaPipe, facial landmark detection, object tracking, pose estimation) for real-time inference on the edge • Optimize models for embedded deployment using quantization, pruning, TensorRT, and NVIDIA Triton • Build and maintain MLOps pipelines for model training, validation, and performance monitoring • Develop video processing pipelines that integrate with both classical signal processing and ML based vital sign extraction • Establish engineering best practices and help reduce technical debt as we scale • Contribute to the architecture and implementation of the computer vision stack from research to production What we look for: • Master's or PhD degree in Machine learning / Computer vision • Strong fundamentals: data structures, CV algorithms, and systems programming • Strong C++ skills - this is critical for our edge deployment pipeline • Solid Python proficiency for ML experimentation and tooling • Ability to work independently, solve complex problems, and drive projects to completion • 5+ years experience deploying computer vision models to production, ideally on resource-constrained devices • Experience with PyTorch and model optimization for edge AI • Proven ability to take models from research to production on embedded hardware Nice to haves: • Experience with NVIDIA Jetson platform, TensorRT, or Triton Inference Server • MLOps experience (experiment tracking, model versioning, performance monitoring) • Experience with sensor fusion (RGB, IR, depth cameras) • Background in medical devices, regulated environments, or healthcare applications • Experience working in fast-moving early-stage environments What we offer: • Real impact: your code provides care for patients today • High autonomy and technical ownership - you'll shape our computer vision architecture • Work at the intersection of cutting-edge AI, edge computing, and healthcare • A talented, excellent, diverse and international team • Cutting-edge stack: embedded AI, robotics, LLMs, multimodal sensing • Talented, international team tackling meaningful problems in remote patient monitoring • Competitive salary • Transparent, mission-driven culture focused on continuous learning

Requirements

Must-haves

Norbert is building autonomous robots that deliver healthcare.
We're not building demos. We're deployed in real facilities today, monitoring hundreds of patients daily. We're solving one of healthcare's hardest problems: a global nursing shortage that will hit 40% by 2030.
We're a small, international team backed by top-tier VCs, with offices in Brooklyn and Paris. We ship things that matter.
The position
We are looking for our lead deep learning engineer to spearhead the development of our groundbreaking sensing technology.
Design, fine-tune, and deploy computer vision models (YOLO, InsightFace, MediaPipe, facial landmark detection, object tracking, pose estimation) for real-time inference on the edge
Optimize models for embedded deployment using quantization, pruning, TensorRT, and NVIDIA Triton
Build and maintain MLOps pipelines for model training, validation, and performance monitoring
Develop video processing pipelines that integrate with both classical signal processing and ML based vital sign extraction
Establish engineering best practices and help reduce technical debt as we scale
Contribute to the architecture and implementation of the computer vision stack from research to production
Master's or PhD degree in Machine learning / Computer vision
Strong fundamentals: data structures, CV algorithms, and systems programming
Strong C++ skills - this is critical for our edge deployment pipeline
Solid Python proficiency for ML experimentation and tooling
Ability to work independently, solve complex problems, and drive projects to completion
5+ years experience deploying computer vision models to production, ideally on resource-constrained devices
Experience with PyTorch and model optimization for edge AI
Proven ability to take models from research to production on embedded hardware

Nice-to-haves

Experience with NVIDIA Jetson platform, TensorRT, or Triton Inference Server
MLOps experience (experiment tracking, model versioning, performance monitoring)
Experience with sensor fusion (RGB, IR, depth cameras)
Background in medical devices, regulated environments, or healthcare applications
Experience working in fast-moving early-stage environments

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aimlmachine learningpython

Platform: breezy
Effort: medium

Benefits

Benefits detected in the listing.

Vision