MLOps Consolidation and Deployment Enablement Expert (m/f/d)

Design and standardize deployment pipelines for machine learning models from a centralized model registryDevelop robust, scalable, and secure model deployment processes across multiple environmentsIntegrate deployment targets such as Orbital Pipelines and Kubeflow/KServeBuild and maintain wrappers, SDK extensions, and configuration templates for various ML frameworksEnsure compatibility of models across frameworks like TensorFlow, PyTorch, and Scikit-learnCollaborate with MLOps teams and stakeholders to define best practices and standardsImplement monitoring hooks, endpoint health checks, and model serving configurationsTroubleshoot deployment issues, latency problems, and framework incompatibilitiesCreate detailed technical documentation, runbooks, and training materialsSupport knowledge transfer and enable long-term ownership within the internal MLOps team Bachelor’s or Master’s degree in a relevant fieldExperience in MLOps, ML engineering, or related domainsHands-on experience with model registries (preferably Weights & Biases)Advanced proficiency in Python and familiarity with shell scriptingStrong expertise in Docker and container orchestration (preferably Kubernetes)Proven experience in building high-availability model serving solutions (REST APIs, gRPC)Experience with deployment frameworks such as Kubeflow, KServe, or similar toolsSolid knowledge of CI/CD tools (e.g., Jenkins, GitLab CI, ArgoCD) and pipeline automationExperience working with cloud environments (preferably AWS)Familiarity with infrastructure-as-code concepts (e.g., Terraform) and scalable system design 30 days leave per yearA highly motivated team and an open way of communication A very renowned companyWe will give you valuable tips and feedback on your application documents and interviewsWe will create a candidate profile containing your strengths and potential and thus increase your chance of being placed in a positionYou will work in an international environment With over 15 years of experience in the pharmaceutical and chemical industry as well as in biotechnology and medical engineering, we know the key contacts at companies that are recruiting for challenging jobs with real potential. The current high demand for staff has opened up exciting opportunities for dedicated experts who want to develop professionally and to further their careers. As recruitment specialists with an international network of contacts, we can offer you decisive advantages – completely free of charge. Register with us and reap the benefits of interesting job offers that match your skills and experience.

Responsibilities

Design and standardize deployment pipelines for machine learning models from a centralized model registryDevelop robust, scalable, and secure model deployment processes across multiple environmentsIntegrate deployment targets such as Orbital Pipelines and Kubeflow/KServeBuild and maintain wrappers, SDK extensions, and configuration templates for various ML frameworksEnsure compatibility of models across frameworks like TensorFlow, PyTorch, and Scikit-learnCollaborate with MLOps teams and stakeholders to define best practices and standardsImplement monitoring hooks, endpoint health checks, and model serving configurationsTroubleshoot deployment issues, latency problems, and framework incompatibilitiesCreate detailed technical documentation, runbooks, and training materialsSupport knowledge transfer and enable long-term ownership within the internal MLOps team

Benefits

30 days leave per yearA highly motivated team and an open way of communication A very renowned companyWe will give you valuable tips and feedback on your application documents and interviewsWe will create a candidate profile containing your strengths and potential and thus increase your chance of being placed in a positionYou will work in an international environment