JOBSEARCHER

Senior Cloud Platform Engineer (AWS), AI Infrastructure - Evinova

Overview: As a Senior Cloud Platform Engineer on the ML/AI Ops team, you design, build and operate the AWS-based platform that powers production Generative AI workloads. You enable AI Engineers and Data Scientists to deploy, scale and secure their solutions with reusable infrastructure and CI/CD patterns. You work across AWS services, IaC, and observability to ensure reliability in a highly regulated environment. This role combines platform engineering with hands-on coding to advance production readiness and developer experience. You'll collaborate across ML/AI, software, security, and product teams to move prototypes into robust, scalable services. Compensation / Benefitshybrid work with office three days a weekcompetitive base salaryshort-term incentive bonusequity-based long-term incentive program 401(k) retirement planpaid vacation and holidays; paid leaves and health benefits (medical, dental, vision)
Responsibilities:
  • Design, build and operate scalable AWS cloud platform capabilities for production ML/AI and Generative AI workloads
  • Create reusable infrastructure, tooling and deployment patterns for independent deployment by AI Engineers and Data Scientists
  • Write and maintain AWS IaC (CDK) in TypeScript and/or Python and develop reusable constructs
  • Build and operate containerized workloads using Amazon ECS and AgentCoreDevelop platform capabilities across compute, networking, IAM, secrets, storage, model access and workload isolation
  • Build CI/CD and GitOps pipelines for safe, automated deployments
  • Partner with engineering teams to transition prototypes to production-grade services
  • Create self-service automation to improve developer experience and reduce toil
  • Engineer platform reliability, scalability and observability to support GenAI workloads
  • Implement monitoring, SLOs, runbooks and production-readiness standards
  • Automate operational processes and optimize costs
  • Contribute to AI gateway and model access controls and routing
  • Ensure security, governance and compliance in a regulated environment
  • Support multi-provider model routing, quotas, rate limits and provider abstraction
  • Drive cost attribution and observability for AI workloads
Key requirements:
  • 4+ years in platform engineering, SRE, DevOps or similar with infrastructure as code output
  • Strong AWS cloud engineering experience in production environments
  • Hands-on experience with Bedrock, ECS, IAM, VPC, load balancing, S3, CloudWatch, Secrets Manager
  • Proficiency with IaC (AWS CDK in Python/TypeScript; Terraform welcome)
  • Docker and ECS experience with production-grade deployments and troubleshootingCI/CD and/or GitOps pipelines for production workloads
  • Knowledge of high availability, scalability, security and cost optimization
  • Proficient Python and/or TypeScript with production tooling
  • Experience with observability tools such as CloudWatch, Open
  • Telemetry, Datadog, Splunk
  • Experience collaborating with ML/AI teams to move workloads to production
  • Strong communication skills and cross-team collaboration
Platform-minded Operationally focused Hands-onAWS CDK (Python/TypeScript)AWS services: Bedrock, ECS, IAM, VPC, S3, CloudWatch, Secrets Manager Terraform (skills welcomed)