Main task of a Software Engineer with focus on MLOps is to create a robust, performant, and self-healing edge or cloud frameworks for the deployment of AI models. These include the connectivity to input sources and output sinks with all steps monitored and containerized. As a Software Engineer with focus on MLOps, you will play a crucial role in building and scaling our ML systems, ensuring they are robust, scalable, and seamlessly integrated into our products and services.
The following challenges await you :
- Design, build, and maintain the infrastructure and tools to deploy, monitor, and manage ML models in production.
- Work closely with data scientists and data engineers to create scalable, efficient, automated pipelines that ingest, process, and analyze large datasets.
- Responsibility for orchestrating and scheduling platforms (e.g. Dataiku) and solutions.
- Implement robust data validation and testing frameworks to ensure the accuracy and integrity of data and models.
- Collaborate with cross-functional teams to ensure that ML solutions meet business requirements and align with company goals.
- Responsible for interfacing to hardware such as cameras – GPIO ports or sensors.
Your profile :
Equivalent job experience or a Master’s in Computer Science, Engineering, Physics, or a related fieldAt least 2- years of experience in a role focusing on ML model deployment, management, and scalabilitySolid knowledge of Linux and networking protocols (udp, grpc, mqtt), including kernel configurations and yocto buildsExpert knowledge in microservice architecture : docker, Kubernetes, streaming (kafka), logging and database (redis, sql) architecturesGeneral knowledge about MLOps concepts (e.g., reproducibility, testing, monitoring), with a focus on connecting different platforms (e.g., labeling platform, artifact store, training infrastructure) to drive automationExperienced with model deployment frameworks such as NVIDIA Triton inference server, and with programming streaming solutions with deepstream for Nvidia edge hardware : Jetson Xavier / OrinExpert knowledge in modern Python development, including knowledge about best practices package management, linting / formatting, data validation, general code design (design patterns), parallelization, and CI / CD with unit and integration testsProfound experience with cloud services (e.g. AWS, Azure, Google)Advanced knowledge in C, C++. Familiar with.NET is a plusWhat you can look forward to at our Consulting Unit :
Empowerment & Career Development - value-adding projects including multiple insights, high visibility and a cross-functional network enabling a future transition into a management or leadership role within the Heraeus GroupTop projects with high impact - You will always work on key topics that are highly relevant for the performance of the Heraeus Group and thus create real added value side by side with our colleagues in the business unitsStrong salary package - attractive basic salary, performance-related components & profit-sharing) and support for private pension planHybrid working and regular time off - a combination of remote and on site working, 30 days annual leave plus up to 6 additional days off (company closures on bridge days and between years), special leave for special occasions, life phase account for paid time off (e.g. sabbatical, earlier retirement)Additional benefits - on site- subsidized public transport, company medical service with comprehensive vaccinations and preventive medical check-ups, sport offers at our Heraeus Balance Point, delicious and healthy dishes in our canteen and social counseling to foster and ensure mental health