Embedded Edge AI Architect

Trebecon LLC
yesterday

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Remote

Tech stack

Artificial Intelligence
Data analysis
C++
Nvidia CUDA
Information Engineering
Data Integrity
Linux on Embedded Systems
Embedded Software
Firmware
Field-Programmable Gate Array (FPGA)
FreeRTOS
Python
Machine Learning
Multipoint Control Unit
OpenGL
OpenCL
Performance Tuning
Real-Time Operating Systems
TensorFlow
DataOps
Signal Processing
Data Processing
Graphics Processing Unit (GPU)
Cloud Platform System
High Performance Computing
PIC Microcontroller
Data Ingestion
PyTorch
Delivery Pipeline
ONNX (Open Neural Network Exchange) Format
Real Time Data
Data Management
TensorRT
Data Pipelines

Job description

We are seeking an experienced Embedded Edge AI Architect with strong expertise in AI/ML modeling, embedded systems, and telemetry-driven performance optimization. The ideal candidate will have hands-on experience developing and deploying AI solutions on embedded platforms such as ARM processors, GPUs, DSPs, FPGAs, and MCUs, with a strong background in Python, C/C++, and Edge AI frameworks.

Requirements

  • 8-10+ years of experience in Embedded Systems, Edge AI, AI/ML, Data Engineering, Telemetry, or Applied Data Science.
  • Strong proficiency in Python for data processing, AI/ML modeling, and pipeline development.
  • Hands-on experience with C/C++ for embedded software and firmware integration.
  • Experience developing and deploying Edge AI applications on embedded devices.
  • Strong knowledge of AI/ML frameworks such as TensorFlow, PyTorch, TensorFlow Lite, Core ML, TensorRT, or ONNX Runtime.
  • Experience working with embedded platforms including ARM processors, NVIDIA GPUs, DSPs, FPGAs, or Microcontrollers (MCUs).
  • Proven experience designing and building telemetry pipelines, data ingestion frameworks, and data models.
  • Experience translating hardware and firmware telemetry into structured datasets for analytics, performance tuning, and machine learning.
  • Strong understanding of time-series data, signal processing, and real-time data systems.
  • Experience developing firmware-to-application interfaces and telemetry ingestion pipelines.
  • Ability to work across multiple system layers, including embedded devices, transport, host systems, and data platforms.
  • Familiarity with GPU-accelerated computing and high-performance computing environments.
  • Experience collaborating with firmware, hardware, and platform engineering teams.
  • Experience designing performance optimization models based on telemetry, workload behavior, thermal constraints, and system utilization.

Preferred Qualifications

  • Experience deploying AI inference pipelines on NVIDIA Jetson, CUDA, or TensorRT.
  • Experience building Edge AI applications using Core ML, Metal, TensorFlow Lite, or OpenCL/OpenGL ES.
  • Knowledge of Embedded Linux environments.
  • Familiarity with RTOS concepts such as Zephyr or FreeRTOS.
  • Experience with platform management protocols such as MCTP and PLDM.
  • Exposure to hybrid Edge/Cloud architectures.
  • Experience with data observability, telemetry validation, and data integrity frameworks.
  • Background in hardware-centric environments such as IoT, Robotics, Autonomous Systems, Consumer Devices, or Industrial Automation.

Key Technologies

  • Programming: Python, C/C++
  • AI/ML: TensorFlow, PyTorch, TensorFlow Lite, Core ML, TensorRT, ONNX Runtime
  • Embedded Platforms: ARM, NVIDIA GPU, DSP, FPGA, MCU
  • Operating Systems: Embedded Linux, RTOS (Zephyr, FreeRTOS)
  • GPU Technologies: CUDA, TensorRT
  • Telemetry & Analytics: Time-Series Data, Signal Processing, Data Pipelines
  • Protocols: MCTP, PLDM

Apply for this position