Lead AI Infrastructure Engineer

Sift Healthcare is seeking a skilled and motivated AI Infrastructure Engineer to design, optimize, and manage AI and ML systems at scale. This role is focused on AI infrastructure, security, and deployment rather than direct model development. The ideal candidate will have expertise in AI model deployment, cloud infrastructure, security, and automation within AWS.

Experience working with PII/PHI/HIPAA data and healthcare data is required for this role.

Responsibilities

• Design, implement, and manage AI/ML infrastructure within AWS, ensuring high availability, scalability, and security.
• Develop and maintain infrastructure-as-code (IaC) using Terraform and AWS CDK to provision and manage cloud resources.
• Ensure compliance with HIPAA and other data privacy regulations, implementing security best practices for handling sensitive healthcare data.
• Design and manage high-performance data pipelines to optimize AI/ML workloads, ensuring secure, scalable, and efficient integration with Snowflake, S3, and vector databases.
• Provide incident response and troubleshooting support for AI infrastructure and production ML models.
  
  

Qualifications

• Bachelor’s degree or higher in Computer Science, Engineering, or a related field.
• Proven experience in AI infrastructure or DevOps roles supporting AI/ML workloads.
• Experience developing, launching, and maintaining APIs.
• Strong proficiency in AWS services (SageMaker, EC2, EKS, S3, Lambda, IAM).
• Hands-on experience with containerization (Docker, Kubernetes, EKS) for scalable AI model deployment.
• Expertise in infrastructure-as-code (Terraform, Terragrunt, AWS CDK, CloudFormation).
• Familiarity with cost optimization strategies for AI workloads on AWS.
• Strong understanding of monitoring, logging, and alerting for AI systems using tools like Prometheus, CloudWatch, and Datadog.
• Experience implementing security best practices for AI workloads, including IAM policies, data encryption, and role-based access control (RBAC).
• Experience deploying, scaling, and optimizing inference for LLMs like GPT, Llama, or Mistral within cloud environments
• Experience working with vector databases (Milvus, Pinecone, Weaviate) and semantic search applications.
• Experience with LLM tooling like Langsmith to support development
• Knowledge of retrieval-augmented generation (RAG) pipelines and hybrid search implementations.
• Familiarity with real-time model inference strategies and optimizations.
  
  

Compensation

Compensation will be based on skills, experience, and performance.

About Sift Healthcare

Sift is a data science company working to improve payments operations and outcomes in the healthcare industry. We are a growing and dynamic team that is serious about technology. Based in Milwaukee, Wisconsin, Sift is thriving and looking for motivated team members who will help shape our culture. Sift offers competitive salaries and benefits. Learn more about Sift at www.sifthealthcare.com.

SCAM ALERT: There is an active nationwide employment scam which is now using Sift Healthcare to garner personal information or financial scams. This site is secure, and any applications made here are with our legitimate partner. If a Sift Recruiter contacts you, please ensure whomever is contacting you truly represents Sift Healthcare. We will never ask for the exchange of any money or credit card details during the recruitment process. Please be aware of any suspicious email activity from people who could be pretending to be recruiters or senior professionals at Sift.