Embedded AI/ML Developer

Jobtailor; Spring (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

Jobtailor is seeking an experienced embedded AI/ML engineer to design, implement, and optimize software for edge devices across PCs, docking solutions, displays, and peripherals. You will translate research models into production firmware with low latency, memory, and power footprints.

You will work with hardware, firmware, software, and data science teams to define requirements, integration plans, and validation procedures, while profiling and tuning workloads for performance and energy

Qualifications

• Bachelor’s or Master’s degree in a technical field (CS/CE/AI/Robotics).
• 7–10 years in embedded software, AI/ML deployment or edge inference.
• Hands-on experience deploying AI on embedded systems and constrained devices.
• Experience with model optimization (quantization, pruning) and deployment toolchains.
• Strong ML inference knowledge and real-time performance tuning.
• Familiarity with RTOS/Linux/Windows and low-level software environments.
• Proficient in C/C++ and Python; experience with AI frameworks (PyTorch, TensorFlow, ONNX).
• Knowledge of sensors, devices, data flow, and hardware interfaces.

Responsibilities

• Design, develop, and optimize embedded AI/ML software for edge devices.
• Convert AI/ML models into production-ready implementations optimized for latency, memory, and power.
• Integrate inference engines, model runtimes, and accelerators into firmware and system software.
• Collaborate with hardware, firmware, software, and data science teams on requirements and architecture.
• Profile and tune embedded AI workloads to improve inference performance and memory footprint.
• Develop interfaces between AI components, firmware, drivers, sensors, and host apps.
• Support model compression and deployment using embedded frameworks and hardware acceleration tech.
• Troubleshoot complex system-level issues across AI inference, firmware, sensors, and platform integration.
• Create and maintain architecture docs, design specs, validation procedures, and deployment notes.
• Explore emerging embedded AI topics to drive innovation across future HP platforms.

Skills

Embedded Software Development

AI/ML Model Deployment

C/C++ Programming

Python Programming

Model Optimization Techniques

Hardware/Software Co-Optimization

Multi-Threaded Development

Real-Time Execution

Sensor Input Handling

Debugging and Profiling

Education

Bachelor’s or Master’s in CS/CE/AI/Robotics

Tools

TensorRT

ONNX

TFLite

PyTorch

TensorFlow

OpenVINO

RTOS

Linux

Windows

JTAG

Job description

• Design, develop, and optimize embedded AI/ML software for edge devices, including PCs, docking solutions, displays, peripherals, and other intelligent client platforms
• Convert AI/ML algorithms and proof-of-concept models into efficient, production-quality embedded implementations optimized for latency, memory, power, and compute constraints
• Integrate machine learning inference engines, model runtimes, and AI accelerators into embedded firmware and system software environments
• Collaborate with hardware, firmware, software, and data science teams to define AI feature requirements, system architecture, data flow, model deployment strategy, and validation plans
• Profile and tune embedded AI workloads to improve inference performance, reduce memory footprint, improve responsiveness, and optimize power consumption
• Develop and maintain software interfaces between AI/ML components, firmware, device drivers, sensors, embedded controllers, and host applications
• Support model compression, quantization, pruning, benchmarking, and deployment using embedded AI frameworks and hardware acceleration technologies
• Troubleshoot complex system-level issues involving AI inference, firmware behaviour, sensor data, device communication, and platform integration
• Create and maintain technical documentation, including architecture descriptions, design specifications, model deployment guides, validation procedures, and integration notes
• Explore emerging embedded AI, TinyML, NPU, MCU, sensor fusion, and edge inference technologies to drive innovation across future HP platforms

Requirements

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Statistics, Mathematics, Artificial Intelligence, Machine Learning, Robotics or a related technical discipline
• 7–10 years of relevant experience in embedded software, firmware, AI/ML deployment, edge inference, or system-level software development
• Hands‑on experience deploying AI/ML models on embedded systems, edge devices, MCUs, SoCs, NPUs, DSPs, or other constrained compute platforms
• Experience with model optimization techniques such as quantization, pruning, compression, TensorRT, ONNX, TFLite, or similar deployment toolchains
• Strong understanding of ML inference pipelines, data preprocessing, sensor input handling, feature extraction, and runtime performance tuning
• Experience integrating AI workloads with embedded firmware, device drivers, RTOS, Linux, Windows, or low‑level system software environments
• Familiarity with AI validation, automated testing, CI/CD pipelines, model benchmarking, and regression testing for embedded platforms
• Strong embedded software development experience using C/C++ and Python
• Experience working with sensors, camera/audio pipelines, telemetry data, wireless modules, or contextual signals
• Knowledge of embedded communication protocols such as UART, I2C, SPI, USB, PCIe, Bluetooth, and Wi‑Fi
• Ability to read hardware specifications, device datasheets, schematics, and platform architecture documents
• Proficiency in C/C++ and Python
• Experience with AI/ML frameworks and formats such as PyTorch, TensorFlow, ONNX, TensorFlow Lite, and OpenVINO
• Knowledge of embedded system architecture, boot flow, firmware interfaces, memory constraints, power management, and real‑time execution tradeoffs
• Skilled in embedded debugging and profiling using JTAG, SWD, logic analyzers, oscilloscopes, performance counters, tracing tools, or vendor‑specific debug environments
• Experience optimizing AI workloads for latency, throughput, memory footprint, thermal behavior, and battery life
• Familiarity with AI accelerator SDKs, NPU/DSP/GPU offload, heterogeneous compute, and hardware/software co‑optimization
• Understanding of RTOS concepts, Linux/Windows system software, multi‑threaded development, secure update mechanisms, and production‑quality embedded software practices
• Ability to work independently and collaboratively in a cross‑functional engineering environment

Core Competencies

Demonstrates expertise in designing and optimizing embedded AI/ML software for edge devices, with a strong focus on model deployment, performance tuning, and integration with hardware and firmware. Proficient in utilizing AI frameworks and optimization techniques to enhance system efficiency and responsiveness.

Highest-signal resume keywords

• Embedded Software Development
• AI/ML Model Deployment
• C/C++ and Python Proficiency
• Model Optimization Techniques
• Integration with Embedded Firmware

ATS Optimization Keywords

Hard Skills

• Embedded Software Development
• AI/ML Model Deployment
• C/C++ Programming
• Python Programming
• Model Optimization Techniques
• AI/ML Frameworks
• Embedded System Architecture
• Debugging and Profiling
• Machine Learning Inference Pipelines
• Sensor Input Handling

Soft Skills

• Collaboration
• Problem‑Solving
• Independent Work

Industry Keywords

• Embedded AI
• Edge Inference
• AI Validation
• Model Benchmarking
• Firmware Interfaces
• Communication Protocols
• Hardware/Software Co‑Optimization
• Multi‑Threaded Development
• Real‑Time Execution
• Cross‑Functional Engineering

Tools & Technologies

• TensorRT
• ONNX
• TFLite
• PyTorch
• TensorFlow
• OpenVINO
• RTOS
• Linux
• Windows
• JTAG