Member of Technical Staff, Backend, LLM Applications
San Mateo
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 5+ yearsEducation: bachelorsSkills: ["Python","Async","Distributed systems","Kubernetes","CI/CD","Cloud infrastructure","AWS","Azure","Load balancing","Terraform","Prometheus","Grafana","Triton Inference Server","TensorRT-LLM","VLLM"]Experienced backend engineer focused on production-grade infrastructure for diffusion LLMs, designing scalable services, model serving endpoints, and zero-downtime deployments. You will optimize latency, throughput, and cost while building observability tooling and infrastructure to support billions of inferences. Work sits at the intersection of ML systems and backend infrastructure in a cutting-edge AI startup.
