MLOps Engineer

Andersen is a global software development company with over 18 years of experience supporting businesses worldwide in their digital transformation. Headquartered in Poland, we operate development centers across multiple countries including Germany, the USA, the UK, and others. We offer end-to-end IT services ranging from custom software development, API integration, system architecture to legacy modernization and long-term support. Our expertise includes AI, Machine Learning, Data Science, Big Data, and Visual Technologies, delivering intelligent and scalable digital products. Andersen serves various industries such as Healthcare, FinTech, Logistic, Automotive, Manufacturing, and E-commerce.

• Strong engineering experience across Software Engineering, DevOps/SRE, and MLOps for 5+ years.
• Production ownership of machine learning systems including operation, support, and accountability.
• Deep hands-on experience with Docker and Kubernetes, including resource management and GPU workloads.
• Strong proficiency with GitLab CI, GitHub Actions, ArgoCD, or equivalent CICD tools including pipeline-enforced quality gates.
• Extensive experience with MLflow, Kubeflow, Feast, BentoML, KServe, SageMaker, Vertex AI, Databricks, or comparable platforms.
• Production engineering standard proficiency in Python (typed, tested, packaged, and reviewed).
• Hands-on LLMOps experience including model gateways, prompt versioning, RAG pipelines, vector databases, evaluation harnesses, and guardrail frameworks.
• Experience in generative AI consumption management including token metering, cost attribution, budget and quota controls, and cost optimization of LLM workloads.
• Experience operating agentic AI systems in production.
• Experience establishing ML platform capabilities from early stage.
• Experience with data quality frameworks and workflow orchestration.
• English language proficiency at upper-intermediate level or above.

Nice to have:

• 10 years of experience in a similar position.

• Designing and owning the end-to-end MLOps architecture for production Machine Learning and Generative AI systems.
• Building and maintaining ML training, validation, deployment, serving, monitoring, and retraining pipelines.
• Building and maintaining CI/CD pipelines for ML and AI workloads with automated testing, approval controls, and rollback mechanisms.
• Collaborating closely with Platform Engineering to run AI workloads on shared Kubernetes infrastructure.
• Translating ML infrastructure requirements into technical requirements for platform and architecture teams.
• Establishing reusable MLOps project templates, shared pipeline components, and engineering standards.
• Building and operating the production layer for Generative AI and LLM-based applications.
• Implementing LLM model gateways, routing, prompt management, prompt versioning, caching, and rate limiting.
• Optimizing LLM workloads through model routing, prompt/context optimization, caching, batching, and selection of cost-efficient models.
• Making and documenting architectural and build-vs-configure decisions for new AI capabilities.