Senior Cloud Platform Engineer (AWS), AI Infrastructure - Evinova
AstraZeneca1 day ago
Mississauga, CanadaSenior
Responsibilities
- Design, build, and operate AWS cloud platform capabilities for production ML/AI and Generative AI workloads.
- Create reusable AWS CDK constructs, infrastructure tooling, deployment patterns, and self-service capabilities for engineering teams.
- Operate containerized workloads using Amazon ECS and AgentCore, including compute, networking, IAM, secrets, storage, and workload isolation.
- Build and maintain CI/CD and GitOps workflows for safe, automated, repeatable, multi-environment deployments.
- Implement autoscaling, load balancing, retries, timeouts, fallback, rate limiting, failure recovery, monitoring, alerting, SLOs, and production-readiness standards.
- Troubleshoot production issues across cloud infrastructure, containers, applications, and model-provider layers, including on-call and incident response.
- Build a centralized AI gateway supporting model routing, provider abstraction, authentication, quotas, fallback, rate limiting, and cost controls.
- Provide secure access to foundation models through Amazon Bedrock and other model platforms.
- Implement observability for token usage, latency, throughput, errors, model performance, and cost attribution using standardized tracing, logging, metrics, and alerting.
- Develop telemetry and data pipelines for evaluating and monitoring production LLM behavior while supporting security, governance, auditability, and regulated-industry compliance.
- Partner with software, data, ML/AI, security, infrastructure, and product teams to transition experimental workloads into reliable production services.
Requirements
- At least 4 years of hands-on experience in platform engineering, infrastructure, SRE, or DevOps roles where infrastructure code was the primary output.
- Deep hands-on experience designing, deploying, and operating production AWS cloud-native infrastructure.
- Strong experience with AWS services including Bedrock, ECS, IAM, VPC, load balancing, S3, CloudWatch, and Secrets Manager.
- Strong infrastructure-as-code experience; AWS CDK with Python and/or TypeScript is preferred, and experienced Terraform engineers are welcome.
- Strong Docker and Amazon ECS experience, including deployment, autoscaling, resource management, health checks, networking, security, and production troubleshooting.
- Experience designing and maintaining CI/CD and/or GitOps pipelines for production cloud workloads.
- Strong understanding of high availability, scalability, resiliency, observability, performance, security, and cost optimization.
- Experience with on-call rotations, incident response, and root-cause analysis for production systems.
- Strong Python and/or TypeScript software engineering skills for production-quality platform tooling and automation.
- Experience implementing production observability with tools such as CloudWatch, OpenTelemetry, Prometheus, Splunk, Datadog, Pydantic Logfire, or Langfuse.
- Experience partnering with software, data, or ML/AI teams to move workloads from experimentation into reliable production environments.
- Preferred experience includes internal developer platforms, Generative AI/LLM production workloads, AI/model gateways, agentic AI, RAG, conversational AI, AgentCore, MCP, LLM evaluation platforms, regulated-industry ML/AI infrastructure, GxP controls, and Kubernetes/Amazon EKS.
- Strong written and verbal communication, documentation, collaboration, organization, autonomy, and ability to work across multiple engineering disciplines.
Benefits
- Hybrid work model in the Greater Toronto Area with employees expected to work from the office three days per week.
- Candidates must live within commuting distance of the GTA or be willing to relocate.
- Permanent roles include a Flex Benefits & Retirement Savings Program, four weeks of paid vacation, annual Personal Days, variable pay bonus/short-term incentive eligibility, and potential equity-based long-term incentive participation.
- Fixed-term contract and temporary positions, excluding students, are offered a Contract Benefits Program.
Tech Stack
Categories
About AstraZeneca
AstraZeneca is a global biopharmaceutical company that discovers, develops, manufactures, and commercializes prescription medicines for patients and healthcare systems. Its portfolio spans oncology, cardiovascular, renal and metabolism, respiratory and immunology, and rare diseases (expanded by the 2021 acquisition of Alexion). Founded in 1999 and headquartered in Cambridge, UK, it is a public company listed on the London Stock Exchange and Nasdaq, generating revenue primarily from drug sales and partnerships.