Software Engineer (m/f/d) Focus on MLOps

Location Hanau
Permanent
Full Time

Solutions from the Heraeus Group provide faster internet, eliminate water of germs, and keep hearts beating in time. As a family-owned global technology group head­quartered in Hanau, Germany, we combine materials expertise and techno­logical leader­ship to create the most diverse products, all with one thing in common: World-class quality. Working with customers around the world, we shape the future and provide vital inno­vations in the areas of Metals & Recycling, Healthcare, Semiconductor & Electronics and Industrials. Heraeus is one of the top 10 family-owned companies in Germany and has a team of around 16,400 employees in 40 countries.

About our Corporate Digital and Consulting Team

As Corporate Consulting and Digitali­zation team at Heraeus, we know the challenges today's global manu­facturing and service companies face. We 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 Operating Companies. We have deep expertise in Supply Chain Excellence (e.g., Operations, Lean Six Sigma) and Commercial Excellence (e.g., Marketing and Sales). We drive digital innovation in our Operating Companies in many different areas, such as Digital Customer Experience (e.g., eCommerce, Web, CRM, Customer Analytics), IoT (e.g., Machine Connectivity, Robotics, Automation, Metrology) and Data Science (e.g., AI, Data Engineering, Optimi­zation). In our Consulting team, we are always in close contact with each other. Openness and trust create room for personal and professional develop­ment. GROW with us and let’s get EXCELLENT together. More information about our Corporate Consulting team can be found at www.heraeus-consulting.com/careers.

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.

• 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.

• Equivalent job experience or a Master’s in Computer Science, Engineering, Physics, or a related field
• At least 2 years of experience in a role focusing on ML model deploy­ment, manage­ment, and scalability
• Solid knowledge of Linux and networking protocols (udp, grpc, mqtt), including kernel configu­rations and yocto builds
• Expert knowledge in micro­service architecture: docker, Kubernetes, streaming (kafka), logging and data­base (redis, sql) architec­tures
• General 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 auto­mation
• Experienced with model deployment frame­works such as NVIDIA Triton inference server, and with programming streaming solutions with deepstream for Nvidia edge hardware: Jetson Xavier / Orin
• Expert 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 tests
• Profound experience with cloud services (e.g., AWS, Azure, Google)
• Advanced knowledge in C, C++. Familiar with.NET is a plus

• 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 Group
• Top 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 units
• Strong salary package — attractive basic salary, performance-related components & profit-sharing and support for private pension plan
• Hybrid 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

We look forward to receiving your documents by reference code 57251 via our online application portal.

Any further questions?

Our Recruiting Team, Corporate Functions, is happy to assist you by email: recruiting.cf@heraeus.com. Or visit us at https://www.heraeus.com/careers.