Member of Technical Staff, Backend, LLM

The Role

We seek experienced backend engineers to own the systems that serve our diffusion LLMs in production. You ll build and operate infrastructure that handles billions of inference requests — optimizing for latency, throughput, cost, and reliability. This role sits at the intersection of ML systems and backend infrastructure.

• Design, build, and operate scalable backend services and model serving infrastructure for our diffusion LLMs.
• Implement and manage load balancing, autoscaling, and traffic routing for model endpoints.
• Build systems for model versioning, canary deployments, and zero-downtime rollouts.
• Develop monitoring, alerting, and observability tooling to ensure SLA compliance and rapid incident response.
• Benchmark and evaluate serving frameworks and hardware configurations to inform infrastructure decisions.

• BS/MS/PhD in Computer Science or a related field (or equivalent experience).
• 5+ years of experience building production backend systems.
• Strong proficiency in Python, including async programming and concurrent systems.
• Solid understanding of distributed systems, networking, and load balancing at scale.
• Familiarity with Kubernetes, CI/CD pipelines, and cloud infra (AWS and/or Azure).

• Experience serving LLMs or other large generative models in production at scale.
• Experience with cloud infrastructure (AWS, Azure), including GPU instance management and cost optimization.
• Experience with infrastructure as code tools (Terraform) and deployment automation.
• Experience with monitoring and observability tools (Prometheus, Grafana).
• Familiarity with model serving frameworks (vLLM, Triton Inference Server, TensorRT-LLM).