Senior Forward Deployed Platform Engineer
R
Recare Deutschland GmbHHealthTech
GermanyFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- English
- Required Skills
- AWSPythonKubernetesFastAPIDatadogGenerative AI
Requirements
- Experience with AWS core services (CloudFormation, IAM, ECR, SageMaker, Bedrock, S3, SQS, DynamoDB, RDS, KMS).
- Experience managing Kubernetes (EKS) in production, including kustomize and HPA/KEDA autoscaling.
- Proven ability to deploy SageMaker models, including custom inference containers and blue/green rollouts.
- Familiarity with observability and LLMOps practices using Datadog, Langfuse, OTel, and CloudWatch.
- Proficiency in Python, specifically FastAPI and async task management.
- Technical knowledge of ML/LLM GPU inference on EKS including Nvidia drivers and plugins.
- Ability to own technical decisions and collaborate effectively across teams.
- Strong troubleshooting and Root Cause Analysis (RCA) skills.
- Excellent written communication skills with a focus on clear documentation.
- Ability to explain complex technical concepts to non-domain experts.
- Fluent English language proficiency.
Responsibilities
- Monitor AI infrastructure to ensure high reliability and performance.
- Manage capacity planning and support scaling initiatives to maintain system stability.
- Execute continuous delivery of SageMaker models following AWS best practices.
- Assist AI engineers in productionalizing AI workloads from code to container build and deployment.
- Implement and manage optimal deployment strategies for AI models.
View Full Description & ApplyYou'll be redirected to the employer's site
