Sr. Software Engineer - AI Platforms and Automation

Own and enhance internal platforms 

• Maintain and enhance internally developed applications and tooling that supports terminology management, content creation, mapping, workflow automation, and content delivery.  

• Build and maintain integrations across internal applications, APIs, knowledge bases, databases, and AI services.  

• Contribute to the design and implementation of new automation and AI-enabled capabilities as business needs evolve.  

Support reliable production systems 

• Own operational support for AI-enabled applications and workflows in production, including troubleshooting, incident response, release coordination, and ongoing maintenance.  

• Manage application deployments, infrastructure configuration, monitoring, alerting, and operational support for AWS-hosted applications and services.  

• Investigate production issues, perform root-cause analysis, and implement durable solutions that improve reliability.  

Enable AI-powered workflows 

• Support AI agents and workflow automation capabilities as they mature from pilot initiatives into scalable production solutions.  

• Develop and troubleshoot cloud-based workflows using AWS services such as Bedrock, Lambda, Glue, S3, IAM, CloudWatch, and MWAA/Airflow.  

• Implement testing, monitoring, and operational readiness practices that improve the quality and reliability of AI-enabled workflows.  

Collaborate across teams 

• Partner with clinical, terminology, product, data science, and engineering teams to improve AI-enabled workflows while maintaining appropriate human review and auditability.  

• Mentor team members and promote software engineering best practices for secure, maintainable, and production-ready systems. 

• Bachelor's or Master's degree in Computer Science, Software Engineering, Data Engineering, Machine Learning, or a related technical field; equivalent professional experience will also be considered. 

• 7+ years of professional experience in software engineering, backend engineering, platform engineering, DevOps, MLOps, cloud engineering, or a related discipline, including experience supporting production systems. 

• Strong proficiency in Python and experience building maintainable services, APIs, internal tools, jobs, or workflow automation in production environments. 

• Experience designing, deploying, and supporting cloud-based applications in AWS environments.

• Experience building or supporting AI-enabled applications using Amazon Bedrock, LLM APIs, knowledge bases, AI agents, retrieval-augmented generation (RAG), or similar technologies. 

• Experience with CI/CD pipelines, Git-based development workflows, automated testing, configuration management, and release practices. 

• Experience with Docker, Kubernetes or other containerized services, Terraform or Infrastructure-as-Code, and production monitoring/alerting tools. 

• Experience with workflow orchestration, data pipelines, or job scheduling tools such as Airflow/MWAA, Glue, Lambda, cron-based jobs, or equivalent technologies. 

• Working knowledge of SQL and relational databases such as PostgreSQL; experience with distributed data or search systems is a plus. 

• Experience building or supporting AI-enabled applications using LLM APIs, retrieval-augmented generation (RAG), knowledge bases, AI agents, or similar technologies. 

• Strong troubleshooting skills, including production issue triage, root-cause analysis, log analysis, and implementation of durable solutions. 

• Ability to partner effectively with domain experts and translate workflow needs into practical, maintainable technical solutions. 

• Strong communication, documentation, and collaboration skills in cross-functional environments.