Together AI
Technical Support Engineer (Inference) - US Weekends
About this role
Join an AI company as a Technical Support Engineer focused on inference services, providing first-line technical support to customers building with Together AI's GPU infrastructure. You'll troubleshoot complex issues, manage Kubernetes-based inference endpoints, and collaborate with product teams to drive improvements—working a 4-day weekend schedule after an initial weekday ramp period.
What you'll do
- Resolve complex technical issues for customers using GPU clusters and inference/fine-tuning services
- Monitor and maintain health, stability, and performance of customer inference endpoints running on Kubernetes
- Serve as last-line technical expert before escalation to Engineering and Product teams
- Execute infrastructure changes via infrastructure-as-code for endpoint configuration, model deployment, and capacity scaling
- Manage customer communications during incidents by translating technical findings into clear, evidence-backed updates
- Identify support patterns and collaborate with teams to inform product roadmap decisions
What they're looking for
- Kubernetes and containerized infrastructure management
- GPU cluster troubleshooting and optimization
- Inference service diagnostics and performance tuning
- Infrastructure-as-code and pull request-based deployments
- API integration and debugging
- Incident communication and customer-facing technical writing
- Monitoring and observability tools (dashboards, log analysis)
- Python or similar scripting for automation
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Together AI
Together AI builds GPU compute infrastructure and open-source model customization platforms for AI developers and enterprises. The company is hiring for infrastructure operations, ML systems engineering, go-to-market technology, customer success, and GPU research roles.
- Website
- together.ai
Likely interview questions
- Describe your experience troubleshooting latency or performance issues in distributed systems—how did you approach diagnosis and resolution?
- Tell us about your experience working with Kubernetes in production environments. What types of issues have you debugged?