Senior Forward Deployed Platform Engineer (m/w/d)

Recare Deutschland GmbH; Deutschland; Remote; USD 140.000 - 180.000; Vollzeit

Benefits dieser Stelle

Edenred card

Birthday day off

Zusammenfassung

Recare Deutschland GmbH is seeking an AI infrastructure engineer to support its European healthcare AI portfolio. You will ensure reliable AI infrastructure and help engineers ship models to production in a regulated environment.

You will monitor, scale, and deploy SageMaker models, implement blue/green rollouts on Kubernetes (EKS), and collaborate with application teams while documenting work for asynchronous communication.

Qualifikationen

• Hands-on experience with AWS services including CloudFormation, IAM, ECR, SageMaker, Bedrock, S3, SQS, DynamoDB, RDS, and KMS.
• Production experience with Kubernetes, ideally EKS, including kustomize and HPA or KEDA-based autoscaling.
• Experience deploying SageMaker models, custom inference containers, and managing provisioning, autoscaling, and blue/green rollouts.
• Familiarity with observability and LLMOps tooling such as Datadog, Langfuse, LLM tracing, OpenTelemetry, and CloudWatch.
• Proficiency in Python with FastAPI and async task management.
• Knowledge of GPU inference setup on EKS, including GPU-backed instances and the Nvidia driver or plugin.
• Comfort owning technical decisions and working cross-functionally with other teams.
• Strong troubleshooting skills with a calm, stepwise approach under pressure.
• Preference for clear written documentation and asynchronous communication.

Aufgaben

• Monitor the AI portfolio to ensure reliable and performant operation for hospitals and aftercare providers.
• Plan capacity, support scaling initiatives, and keep systems stable as usage grows.
• Continuously deliver SageMaker models following AWS best practices.
• Help AI engineers productionalize workloads end to end, from code through container build to rollout.
• Apply optimal deployment strategies including blue/green rollouts for AI services.
• Collaborate directly with application teams on technical decisions that bridge product and platform.
• Document work clearly and communicate asynchronously across the engineering organization.

Tools

AWS CloudFormation

IAM

ECR

SageMaker

Bedrock

S3

SQS

DynamoDB

RDS

KMS

Kubernetes (EKS)

kustomize

HPA

KEDA

Datadog

Langfuse

OpenTelemetry

CloudWatch

Python

FastAPI

Async

GPU inference on EKS

Nvidia driver/plugin

Jobbeschreibung

Role overview

This role supports the AI portfolio of a healthcare technology platform that connects hospitals with rehabilitation clinics and aftercare providers across Europe. The position focuses on making AI infrastructure run reliably and predictably, helping AI engineers ship models safely into production within a regulated environment.

Responsibilities

• Monitor the AI portfolio to ensure reliable and performant operation for hospitals and aftercare providers
• Plan capacity, support scaling initiatives, and keep systems stable as usage grows
• Continuously deliver SageMaker models following AWS best practices
• Help AI engineers productionalize workloads end to end, from code through container build to rollout
• Apply optimal deployment strategies including blue/green rollouts for AI services
• Collaborate directly with application teams on technical decisions that bridge product and platform
• Document work clearly and communicate asynchronously across the engineering organization

Requirements

• Hands-on experience with AWS services including CloudFormation, IAM, ECR, SageMaker, Bedrock, S3, SQS, DynamoDB, RDS, and KMS
• Production experience with Kubernetes, ideally EKS, including kustomize and HPA or KEDA-based autoscaling
• Experience deploying SageMaker models, setting up custom inference containers, and managing provisioning, autoscaling, and blue/green rollouts
• Familiarity with observability and LLMOps tooling such as Datadog, Langfuse, LLM tracing, OpenTelemetry, and CloudWatch
• Proficiency in Python with FastAPI and async task management
• Knowledge of GPU inference setup on EKS, including GPU-backed instances and the Nvidia driver or plugin
• Comfort owning technical decisions and working cross-functionally with other teams
• Strong troubleshooting skills with a calm, stepwise approach under pressure
• Preference for clear written documentation and asynchronous communication

Nice to have

• Familiarity with European sovereign cloud environments and certifications relevant to healthcare such as ISO 27001 or C5
• Experience with Nvidia Triton, vLLM, or similar inference servers
• Exposure to MLflow, Kubeflow, ClearML, DVC, or Vertex AI
• Personal self-hosting or home lab experience
• Building Slack or GitHub automations such as bots and workflows

Benefits and work setup

Remote-friendly company with flexible hours and the option to arrange workations. The culture emphasizes flat hierarchies, mutual respect, and high performance. Additional perks include an Edenred card usable for personal needs and an extra vacation day to celebrate your birthday.