Embedded MLOps Engineer

Are you passionate about deploying cutting-edge machine learning models to the edge and cloud? Do you thrive in a dynamic, fast-paced environment where you can push the boundaries of what's possible with embedded AI and cloud-based ML? If so, we have an exciting opportunity for an Embedded MLOps Engineer to join our team.

As an Embedded MLOps Engineer, you will play a crucial role in developing and deploying machine learning models on a variety of edge devices, including Raspberry Pi, Jetson Nano, Google Coral, Intel Movidius, and ARM-based microcontrollers. You will be responsible for designing and implementing robust data processing pipelines that can seamlessly integrate with these edge systems and the cloud, ensuring efficient and reliable model deployment across the edge-cloud continuum.

Your expertise in technologies such as message brokers, sockets, and message queuing protocols like ZeroMQ, RabbitMQ, or Apache Kafka will be essential in building scalable and highly performant edge and cloud solutions. You will also be comfortable working with both microservices and monolithic architectures, allowing you to adapt to the unique requirements of each project.

# Required Skills and Qualifications

- Proficient in Python, C/C++, and familiarity with embedded systems programming.
- Extensive experience in developing and deploying machine learning models on edge devices.
- Deep understanding of message brokers, sockets, and technologies like ZeroMQ, RabbitMQ, or Apache Kafka for building scalable and efficient edge and cloud data processing pipelines.
- Expertise in designing and implementing robust data processing pipelines that can seamlessly integrate with edge devices and cloud infrastructure, handling various data types such as images, videos, text, and audio.
- Familiarity with microservices and monolithic architectures, and their trade-offs in the context of edge-cloud communication and data flow.
- Experience with container technologies (e.g., Docker, Podman) and container orchestration platforms (e.g., Kubernetes, OpenShift) for deploying and managing edge and cloud-based ML inference services.
- Knowledge of CI/CD tools and practices, such as Jenkins, Travis CI, or GitHub Actions, to automate the deployment of ML models across the edge-cloud continuum.
- Understanding of edge computing challenges, including resource constraints, power management, latency, and offline operation.
- Familiarity with sensor data acquisition, preprocessing, and integration techniques for edge devices, leveraging protocols like SPI, UART, I2C, and more.
- Experience with embedded operating systems, such as Linux (e.g., Raspbian, Ubuntu Server) and real-time OSes (e.g., FreeRTOS, NuttX), and their integration with edge ML inference services.
- Proficiency in embedded systems programming, including low-level hardware interaction, device drivers, and firmware development for seamless data exchange between edge devices and the cloud.
- Strong problem-solving and analytical skills, with the ability to think critically and find creative solutions for edge-cloud ML deployments.
- Excellent verbal and written communication skills, with the ability to effectively collaborate with cross-functional teams.

# Preferred Experience

- Experience working with UAVs, drones, or flight controllers, and their integration with embedded AI systems for real-time inference and data processing.
- Knowledge of robotic frameworks (e.g., ROS, ROS2, Ardupilot) and their application in edge-cloud computing environments for robotics and autonomous systems.
- Familiarity with edge-cloud synchronization protocols and mechanisms, such as MQTT, CoAP, or AMQP, for efficient and reliable data transfer between the edge and the cloud.
- Experience with time-series data analysis and anomaly detection on edge devices, and integrating these insights with cloud-based data analytics and visualization platforms.
- Proficiency in computer vision, natural language processing, or other specialized ML domains relevant to edge-cloud applications, such as industrial automation, smart cities, or environmental monitoring.
- Understanding of data security and privacy considerations for edge-cloud ML deployments, including techniques like federated learning and differential privacy.
- Experience with developing and deploying multi-modal ML models that can seamlessly operate across the edge-cloud continuum, leveraging diverse data sources and sensor modalities.
- Familiarity with edge-cloud hybrid architectures, where certain ML model components or preprocessing steps are performed on the edge, while the rest of the pipeline is executed in the cloud for increased scalability and resource efficiency.

Company Benefits are discussed with Candidates specifically.

If you're ready to revolutionize the world of embedded AI and push the boundaries of what's possible with edge-cloud computing, we encourage you to apply for this exciting Embedded MLOps Engineer role. Join our dynamic team and be a part of shaping the future of intelligent edge and cloud systems.

About Gene Grinyov

Working with stealth Products in Ukrainian Miltech

Company website:
https://www.ggrinyov.com/