Workplace
remote
Employment
Full-Time
Published
Aug 11, 2026
Closes
No date supplied
The role
About the Role
Together AI is building the AI Acceleration Cloud, an end-to-end platform for the full generative AI lifecycle, combining the fastest LLM inference engine with state-of-the-art AI cloud infrastructure.
The AI Infrastructure team at Together AI is at the forefront of building and scaling the foundational systems that power our generative AI platform. The storage and observability team is crucial for designing, implementing, and maintaining robust distributed storage solutions, ensuring seamless data access and management. They are also responsible for developing comprehensive observability platforms, providing critical insights into system performance and GPU utilization, and proactively identifying and resolving issues.
Responsibilities
• Design and implement a scalable observability platform (metrics, logs, traces) using tools like Prometheus, Grafana, ClickHouse, ClickStack, and OpenTelemetry, including telemetry data pipelines and log aggregation workflows.
• Develop automated monitoring, alerting, and anomaly detection systems, including SLIs/SLOs, runbooks, and predictive analytics for critical services.
• Build and deploy custom observability tools and infrastructure-as-code using Go, Python, Terraform, Ansible, and Helm.
• Collaborate with engineering teams to enhance distributed tracing and application monitoring, and lead incident response with post-mortem analysis.
• Define observability best practices.
Requirements
• Expertise in observability platforms (Prometheus, Grafana, ClickStack, OpenTelemetry) and cloud-native monitoring services (AWS, GCP, Azure).
• Strong programming skills in Go, Python, or similar languages, with proficiency in infrastructure-as-code tools (Terraform, Ansible, Helm).
• Experience designing, operating, and scaling large-scale distributed systems and pipelines for
Requirements
Department: Engineering