Senior Forward Deployed Platform Engineer

This is a fully remote position, open to applicants in Germany.

📋 Description

• Ensure the reliable operation and high performance of the AI portfolio.

• Oversee AI workloads and the underlying infrastructure.

• Plan for capacity needs and support scaling efforts.

• Maintain system stability as the organization expands.

• Continuously deliver SageMaker models in accordance with AWS best practices.

• Assist AI engineers in the end-to-end productionization of AI workloads.

• Support workflows from code development to container builds and deployments.

• Implement optimal deployment strategies in a regulated healthcare setting.

• Manage and enhance cloud-native AI infrastructure utilizing AWS, Kubernetes, Postgres, Bedrock, SageMaker, ClearML, Datadog, LangFuse, OTEL, and GitHub Actions.

• Foster collaboration across applications and platform teams through cross-functional teamwork.

⛳️ Requirements

• Proficiency with AWS services including CloudFormation, IAM, ECR, SageMaker, Bedrock, S3, SQS, DynamoDB, RDS, and KMS.

• Experience with Kubernetes (EKS) in a production environment, including kustomize, HPA, and KEDA-based autoscaling.

• Skilled in deploying SageMaker models, creating custom inference containers and endpoints, provisioning, autoscaling, and executing blue/green rollouts.

• Familiarity with best practices and solutions in observability and LLMOps, such as Datadog, Langfuse, LLM/GenAI tracing, OTel, and CloudWatch.

• Strong proficiency in Python, particularly with FastAPI and asynchronous task management.

• Understanding of ML/LLM GPU inference on EKS, GPU-backed instances, and Nvidia driver/plugin.

• Capability to make technical decisions and collaborate effectively with other teams.

• Skills in troubleshooting, root-cause analysis, and problem resolution.

• Ability to maintain composure under pressure and systematically address issues.

• Preference for clear technical documentation and asynchronous communication.

• Competence in conveying complex concepts to non-experts and eliciting information through well-formulated questions.

• Proficiency in English.

• Bonus: Experience in healthcare or regulated domains, such as ISO 27001 or C5.

• Bonus: Background in self-hosting or home lab setups.

• Bonus: Familiarity with Nvidia Triton/vLLM or similar technologies.

• Bonus: Experience with MLflow, Kubeflow, ClearML, DVC, or Vertex AI.

• Bonus: Knowledge of Slack and GitHub automations.

🏝️ Benefits

• A remote-friendly company that offers flexible working hours.

• Opportunities for workations by arrangement.

• Edenred card benefits.

• An extra vacation day on your birthday.

• Meaningful work in the healthcare technology sector.

• Flat organizational structure promoting mutual respect, loyalty, and recognition.