Embedded Deployment Engineer
- Job Title
- Embedded Deployment Engineer
- Job ID
- Boston, MA 02210
- Other Location
Founded in 2017, Activ Surgical is a first-of-its kind digital surgery company focused on improving surgical efficiency, accuracy, patient outcomes and accessibility for both endoscopic and robotically assisted procedures. Activ Surgical’s scalable and patent-protected surgical software platform technology is driven by computer vision, artificial intelligence, analytics, and machine learning to enhance a surgeon’s intra-operative decision making and reduce unintended and preventable surgical complications.
Activ Surgical is looking for individuals who are interested in shaping the future of healthcare by improving patient outcomes, reducing healthcare costs, and addressing unintended surgical complications.
You will join a team where everyone—including you—is striving to constantly create innovative technology. We are an incredibly supportive team–we love to pitch in when problems arise and give great peer feedback to help each other grow. We are passionate about lots of things—artificial intelligence, machine learning, autonomous robotics and a great user experience--and we love sharing those passions with each other.
Fortune 500 Health & Wellness
Flexible Time Off
We are seeking a Embedded Deployment Engineer to join us in a key role on the Data team within our R&D group. In this role, you will work closely with AI/ML and algorithm developers, and the software development team to deliver AI based insights into the operating room.
You will be responsible for optimizing ML models developed in common frameworks such as PyTorch and TensorFlow for specific hardware deployment. You will work on integrating the models with our current software stack for real-time inference at the edge.
- Collaborate with cross-functional teams to understand and support business needs
- Apply your knowledge and experience with different data technologies to build reliable, maintainable, secure, and scalable systems and processes
- Utilize CI/CD best practices in deploying optimized ML models
- Self-motivated with strong problem solving and analytical skills. Ability to communicate across technical and non-technical teams.
- Demonstrated experience optimizing and deploying ML model on edge devices
- Knowledge of ML frameworks and real-time inference frameworks
- Proficiency with Linux, C/C++, Python, TensorRT
- Experience with Triton Inference Server and DeepStream SDK is a plus
- Experience implementing ML operations on CPUs or GPUs is a plus
- Minimum bachelor's degree in a relevant field
- Minimum 2 years prior experience