Tech Stack
AWSCloudDockerKubernetesPythonSQL
About the role
- Build and deploy production-ready AI agents for data processing, data analysis, and workflow automation
- Implement monitoring, error handling, and reliability patterns for AI agent systems
- Build & troubleshoot infrastructure as needed to support agent deployments
- Use evals to measure & improve agent performance
- Work with product management & internal teams to define agent behavior
- Participate in on-call rotation for AI system reliability and incident response
- Help define how we build agentic systems as we transition to building customer-facing features
Requirements
- 1-3 years of software engineering experience with at least 1+ years working with AI/ML systems
- Production AI agent experience - you've built, deployed, and maintained AI agents or autonomous systems in production
- Python proficiency with hands-on experience in AI frameworks, including agents & RAG libraries
- API and integration experience - comfortable working with REST APIs, webhooks, and third-party integrations
- Database experience with SQL and familiarity with data warehouses (Snowflake experience is a plus)
- Infrastructure experience - Docker, AWS/cloud platforms, CI/CD pipelines, K8s, monitoring tools
- AI development tools - you believe in staying on the edge of AI development tools and know how to optimize them for your workflow
- Comfortable moving fast in a loosely structured environment
- Must be comfortable participating in on-call rotation
- Not able to sponsor visas for this position