Edge C++ Engineer — AI Vision & Edge Platform

Coram-Ai; Sunnyvale (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Coram AI is expanding its team in Sunnyvale, CA to build edge computing solutions for real-time vision processing. You will develop edge applications, deploy ML models to production, and optimize runtime performance on constrained devices.

The role emphasizes C++ development on Linux, GPU-accelerated pipelines, and strong collaboration to build observability and telemetry for a high-growth AI security platform.

Qualifications

• A Bachelor's or Master's degree in Computer Science.
• 3-8 years of experience in data structures, algorithms, and object-oriented design.
• Strong programming in C++ and strong understanding of Linux.
• Knowledge of any other development language, including Java, Python, and Shell scripts.
• Edge/IoT computing experience is a plus.
• Infrastructure management experience (Salt) is a plus.
• Monitoring experience (Grafana) is a plus.
• Video processing & streaming experience (GStreamer) is a plus.
• Experience interfacing ML models (PyTorch) is a plus.
• Resilient in challenging and fast-paced environments.
• Exceptional written and verbal communication skills in English.

Responsibilities

• Build edge applications processing vision data and communication layers for the compute-constrained edge devices.
• Deploy machine learning models to production, optimizing the platform runtime for maximum performance.
• Operating largely C++ code with parts of the pipeline running on GPU.
• Build observability and telemetry.

Skills

C++

Linux

English communication

Edge/IoT computing

GStreamer

PyTorch

Grafana

Salt

Java/Python/Shell

Education

Bachelor's or Master's in Computer Science

Tools

GStreamer

PyTorch

Salt

Grafana

Job description

Coram AI is expanding its team in Sunnyvale, CA to build edge computing solutions for real-time vision processing. You will develop edge applications, deploy ML models to production, and optimize runtime performance on constrained devices.

The role emphasizes C++ development on Linux, GPU-accelerated pipelines, and strong collaboration to build observability and telemetry for a high-growth AI security platform.