Senior Software Engineer, Cresta

• 5+ years writing production software; 2+ years focused on ML platform or infra
• Expert Python (async, typing, packaging, performance)
• Working Golang knowledge for systems components
• Proven experience with one or more serving frameworks (e.g., vLLM, Triton, TorchServe)
• Kubernetes and cloud-native ops
• Solid grasp of distributed systems, networking, and container security
• Culture of rigorous testing, code review, and continuous delivery

Desirable

• Own model serving: Design, build, and maintain low-latency, highly-available serving stacks for in-house ML model serving and integrating with LLM serving partners
• Automate training pipelines: Orchestrate data prep, training, evaluation, and registry workflows on Kubernetes with solid MLOps practices
• Optimize at scale: Profile and tune throughput, memory, and cost; introduce caching, sharding, batching, and GPU/CPU autoscaling where it pays off
• Build platform primitives: Create reusable SDKs, templates, and CLI tools that let research and product teams ship models independently and safely
• Raise the bar: Instrument deep observability (tracing, metrics, alerts), drive blameless post-mortems, and mentor engineers on production ML best practices