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

About the Company

Responsibilities

• ● drock AgentCore, Amazon ECS, CI/CD, SageMaker Unified Studio, AI gateways, observability, scalability, reliability, security, governance and cost optimization. Your work will establish reusable platform capabilities that allow teams across Evinova to deploy and operate solutions faster and more reliably while meeting the requirements of a highly regulated pharmaceutical environment.
• ● Accountabilities
• ● Cloud Platform Engineering
• ● Design, build and operate scalable AWS cloud platform capabilities for production ML/AI and Generative AI workloads.
• ● Create reusable infrastructure, tooling and deployment patterns that enable AI Engineers and Data Scientists to independently deploy and operate their applications.
• ● Write and maintain AWS IaC primarily AWS CDK in TypeScript and/or Python, including reusable CDK constructs that other teams consume.
• ● Build and operate containerized workloads using Amazon ECS and AgentCore.
• ● Develop reusable platform capabilities across compute, networking, IAM, secrets management, storage, model access and workload isolation.
• ● Build and maintain CI/CD and GitOps workflows that enable safe, automated and repeatable deployments across environments.
• ● Partner with engineers and Data Scientists to transition prototypes and research workloads into resilient, production-grade services.
• ● Build self-service capabilities and automation that improve developer experience and reduce operational toil.
• ● Reliability, Scalability & Operational Excellence
• ● Engineer platform capabilities that improve the availability, scalability, resiliency and performance of production GenAI workloads.
• ● Design and implement autoscaling, load balancing, retries, timeouts, fallback, rate limiting and failure-recovery strategies.
• ● Establish monitoring, alerting, SLOs, runbooks and production-readiness standards for ML/AI workloads.
• ● Troubleshoot complex production issues across AWS infrastructure, container, application and model-provider layers.
• ● Automate operational processes and proactively identify opportunities to improve platform reliability and performance.
• ● Drive cloud and model cost optimization through capacity management, workload optimization and data-driven analysis.
• ● AI Gateway & Model Access
• ● Build and operate a centralized AI gateway that routes requests across model providers.

Requirements

• ● Minimum of 4 years of hands-on experience in a platform engineering, infrastructure, site reliability engineering (SRE) or DevOps role where infrastructure code was your main output.
• ● Deep hands-on AWS cloud engineering experience, including designing, deploying and operating production cloud-native infrastructure.
• ● Strong experience with AWS services such as Bedrock, ECS, IAM, VPC, load balancing, S3, CloudWatch, Secrets Manager and related services.
• ● Strong hands-on experience with IaC. AWS CDK using Python and/or TypeScript is preferred. Strong Terraform engineers who are willing to work in CDK are welcome.
• ● Strong experience with Docker and Amazon ECS, including workload deployment, autoscaling, resource management, health checks, networking, security and production troubleshooting.
• ● Strong understanding of cloud and platform engineering principles, including high availability, scalability, resiliency, observability, performance, security and cost optimization.
• ● Strong software engineering skills in Python and/or TypeScript, with experience building production-quality platform tooling and automation.
• ● Demonstrated experience partnering with software, data or ML/AI teams to transition workloads from experimentation into reliable production environments.
• ● Proven ability to collaborate effectively across ML/AI engineering, software engineering, security, infrastructure and product teams.
• ● Strong written and verbal communication skills, including the ability to clearly document infrastructure architecture, operational processes and platform standards.
• ● Preferred Skills/Experience
• ● Hands-on experience with Amazon Bedrock or another enterprise foundation-model platform.
• ● Understanding of GxP and/or other controls applicable to regulated ML/AI systems.
• ● This Role Is Not a Good Fit If
• ● Your main experience is building agents, RAG pipelines, prompts or LLM applications, and you have not owned production infrastructure.
• ● You have not written or maintained infrastructure as code for production systems.
• ● You prefer research or model development to operating production platforms.
• ● Personal Attributes
• ● Platform-minded: You think beyond individual applications and build reusable capabilities that enable multiple engineering teams.
• ● Operationally focused: You care about reliability, scalability, observability, security, performance and what happens after a workload reaches production.

Benefits

• ● Evinova is a health-tech business focused on accelerating better health outcomes by advancing digital transformation across the life sciences sector. By combining science-based expertise, evidence-led rigor, and deep human insight, we design digital solutions that enable healthcare to work better for everyone.
• ● Operating at the intersection of healthcare, technology, data, and analytics, we are helping unlock the full potential of digital health, transforming how clinical research is conducted, how care is delivered, and how patients experience healthcare. Our solutions are built to scale, driving efficiency, improving decision-making, and ultimately delivering better outcomes for patients worldwide.
• ● At Evinova, we are driven by a shared purpose to transform health through data and digital innovation. Our teams collaborate across disciplines to solve complex challenges, continuously learning and evolving in a fast-paced, high-impact environment.
• ● We also recognize the importance of flexibility and balance. Our ways of working support both individual needs and team collaboration. To foster connection and collaboration, employees are expected to work from the office three days per week , creating opportunities for in-person teamwork, innovation, and meaningful connection.
• ● This role is located in Gaithersburg, Maryland and follows a hybrid work model. Candidates must reside within commuting distance of Gaithersburg or be willing to relocate for this opportunity.