Principal Edge AI Engineer
About the Role
To Apply for this Job Click Here
Job Description
- Lead the design and development of AI/ML-enabled telemetry pipelines across GPU-enabled embedded and edge systems, enabling real-time analytics and performance optimization
- Develop software, algorithms, and C++-driven firmware components for AI systems running on embedded GPUs, ARM MCUs, DSPs, and FPGAs
- Build and deploy deterministic Edge AI pipelines on NVIDIA platforms to support low-latency inference and system-level decisioning
- Develop and optimize Edge AI applications across Apple (Core ML + Metal) and Android devices (TensorFlow Lite GPU runtime, OpenCL/OpenGL ES)
- Design and implement end-to-end data pipelines transforming low-level system telemetry (via C++/firmware interfaces) into structured datasets for analytics, ML, and performance tuning
- Translate GPU, thermal, and workload telemetry into actionable insights, optimization strategies, and automated control mechanisms
- Partner with firmware, hardware, and platform engineering teams to ensure scalable, high-quality data capture and integration across system layers
- Define data models, schemas, and interface contracts to enable reliable data ingestion, observability, and AI-driven system intelligence
Requirements
- 10+ years of experience in AI/ML engineering, data engineering, telemetry systems, or embedded/edge computing environments
- Strong experience developing AI software, algorithms, and C++-based systems/firmware for embedded platforms (GPUs, ARM MCUs, DSPs, FPGAs)
- Proven expertise building and optimizing Edge AI solutions across devices (Core ML, Metal, TensorFlow Lite, GPU runtimes)
- Proficiency in Python for data modeling, pipeline development, and ML-related data processing
- Strong working expertise in C++ for low-level system integration, firmware interfacing, and performance-sensitive components
- Experience designing and implementing telemetry pipelines and transforming hardware/firmware signals into structured datasets for analytics or ML
- Strong understanding of time-series data, signal processing, and real-time system constraints in AI/edge environments
- Experience analyzing system-level telemetry (GPU utilization, thermals, workload behavior) to drive performance optimization and AI-driven decisioning
1460932_1782765786
To Apply for this Job Click Here
Excited about this job?
Don’t wait — Step into a role that matches your potential!
Explore Similar Roles
See more jobs like this in your inbox weekly.
Share this Role
Other jobs you might like...
What job seekers like you say about working with Beacon Hill…
Substance. Scale. Synchrony.
Beacon Hill is an Equal Opportunity Employer that values the strength diversity brings to the workplace. Individuals with Disabilities and Protected Veterans are encouraged to apply.
Founded by industry leaders to set a new standard in search, career placement and flexible staffing, we deliver coordinated staffing solutions with unparalleled service, and a passion for innovation, creativity and continuous improvement.
Our niche brands offer a complete suite of staffing services to emerging growth companies and the Fortune 500 across market sectors, career specialties/disciplines and industries. Over time, office locations, specialty practice areas and service offerings will be added to address ever changing constituent needs.
We look forward to working with you.