Computer Vision Engineer (Real-Time / Edge AI)
Company Description
Operis is revolutionizing anesthesia practices with its AI-powered co-pilot. Leveraging cutting-edge computer vision and proprietary machine learning models, the platform identifies syringes, vials, and drug volumes with precision, streamlining documentation and automating reconciliation. By flagging potential medication errors in real time and optimizing inventory management, Operis Health enhances patient safety and improves operational efficiency.
The company is at the forefront of innovation, utilizing video capture technologies to transform healthcare processes.
• We are a
spinout of an established healthcare technology company.
• We have
already secured NIH funding to develop and validate this system in clinical workflows.
• We are backed by
seed capital and are actively building toward real-world deployment.
• Our business and clinical leadership team includes experienced operators in healthcare, medical devices, and enterprise software.
This is an opportunity to work on a
high-impact, technically challenging system at the intersection of computer vision, edge computing, and patient safety.
Role Description
This is a full-time remote role for a Computer Vision Engineer (Real-Time / Edge AI).
You will be a core contributor to the development of a
real-time, multi-camera computer vision system operating in a complex clinical environment.
Key areas of ownership
• Object detection for medical objects (vials, syringes, hands)
• OCR / label recognition for drug identification
• Multi-frame aggregation and temporal reasoning
• Object tracking and cross-view association
• Real-time inference optimization on edge devices (wearables + local compute)
• Improving robustness to real-world conditions (glare, occlusion, motion, clutter)
You will work closely with:
• Founders
• A fractional AI/ML technical lead
• Systems/embedded engineers
• Clinical stakeholders
Why this role is unique:
• Real-world impact:
This system directly addresses medication safety and clinical workflow in operating rooms.
• Hard technical problems:
Multi-view fusion, real-time constraints, noisy environments, and safety-critical decisioning.
• Strong foundation:
Backed by NIH funding, seed capital, and an existing company with real technology and distribution.
• High ownership:
You will shape core architecture and models—not just tune parameters.
Qualifications
• Experience in designing and implementing real-time CV systems
• Familiarity with frameworks such as TensorFlow, PyTorch, or OpenCV
• Experience with
object detection models
(YOLO, Detectron, etc.)
• Experience working with
video data
(not just static images)
• Ability to debug real-world CV issues including: lighting variability, occlusion, motion blur, cluttered scenes
• Experience building or contributing to production systems
• Master's or Ph.D. in Computer Science, Engineering, or a related field is highly desirable
• Experience in healthcare technology or medical imaging is a plus
Bonus experience
• Multi-view geometry or cross-camera tracking
• Edge deployment (ONNX, TensorRT, mobile/embedded inference)
• OCR or document/label recognition
• Experience with real-time or low-latency systems
• Healthcare, medical device, or regulated environments
Who you are:
• You’ve built real systems
• You are comfortable working with imperfect data and ambiguous problems
• You care about performance, reliability, and practicality
• You can move quickly while making sound technical decisions
Key activities for the first 90 days:
• Build and iterate on detection pipelines using real-world video data
• Improve model performance in challenging OR-like conditions
• Identify and solve key failure modes in object detection and recognition
• Contribute to an end-to-end working system
Compensation:
• Competitive salary + equity, commensurate with experience
• Flexible structure: full-time preferred; contract-to-hire considered for strong candidates
How to apply:
• E-mail your resume to [email protected]
• In the subject line include this: "LinkedI
Operis is revolutionizing anesthesia practices with its AI-powered co-pilot. Leveraging cutting-edge computer vision and proprietary machine learning models, the platform identifies syringes, vials, and drug volumes with precision, streamlining documentation and automating reconciliation. By flagging potential medication errors in real time and optimizing inventory management, Operis Health enhances patient safety and improves operational efficiency.
The company is at the forefront of innovation, utilizing video capture technologies to transform healthcare processes.
• We are a
spinout of an established healthcare technology company.
• We have
already secured NIH funding to develop and validate this system in clinical workflows.
• We are backed by
seed capital and are actively building toward real-world deployment.
• Our business and clinical leadership team includes experienced operators in healthcare, medical devices, and enterprise software.
This is an opportunity to work on a
high-impact, technically challenging system at the intersection of computer vision, edge computing, and patient safety.
Role Description
This is a full-time remote role for a Computer Vision Engineer (Real-Time / Edge AI).
You will be a core contributor to the development of a
real-time, multi-camera computer vision system operating in a complex clinical environment.
Key areas of ownership
• Object detection for medical objects (vials, syringes, hands)
• OCR / label recognition for drug identification
• Multi-frame aggregation and temporal reasoning
• Object tracking and cross-view association
• Real-time inference optimization on edge devices (wearables + local compute)
• Improving robustness to real-world conditions (glare, occlusion, motion, clutter)
You will work closely with:
• Founders
• A fractional AI/ML technical lead
• Systems/embedded engineers
• Clinical stakeholders
Why this role is unique:
• Real-world impact:
This system directly addresses medication safety and clinical workflow in operating rooms.
• Hard technical problems:
Multi-view fusion, real-time constraints, noisy environments, and safety-critical decisioning.
• Strong foundation:
Backed by NIH funding, seed capital, and an existing company with real technology and distribution.
• High ownership:
You will shape core architecture and models—not just tune parameters.
Qualifications
• Experience in designing and implementing real-time CV systems
• Familiarity with frameworks such as TensorFlow, PyTorch, or OpenCV
• Experience with
object detection models
(YOLO, Detectron, etc.)
• Experience working with
video data
(not just static images)
• Ability to debug real-world CV issues including: lighting variability, occlusion, motion blur, cluttered scenes
• Experience building or contributing to production systems
• Master's or Ph.D. in Computer Science, Engineering, or a related field is highly desirable
• Experience in healthcare technology or medical imaging is a plus
Bonus experience
• Multi-view geometry or cross-camera tracking
• Edge deployment (ONNX, TensorRT, mobile/embedded inference)
• OCR or document/label recognition
• Experience with real-time or low-latency systems
• Healthcare, medical device, or regulated environments
Who you are:
• You’ve built real systems
• You are comfortable working with imperfect data and ambiguous problems
• You care about performance, reliability, and practicality
• You can move quickly while making sound technical decisions
Key activities for the first 90 days:
• Build and iterate on detection pipelines using real-world video data
• Improve model performance in challenging OR-like conditions
• Identify and solve key failure modes in object detection and recognition
• Contribute to an end-to-end working system
Compensation:
• Competitive salary + equity, commensurate with experience
• Flexible structure: full-time preferred; contract-to-hire considered for strong candidates
How to apply:
• E-mail your resume to [email protected]
• In the subject line include this: "LinkedI