Senior SRE - foundational AI - Austin

Senior Site Reliability Engineer

Location: Austin, TXI'm working with a growing company building a foundational AI system, engineering something genuinely different from typical LLM-based products.

Founded by veterans of top-tier trading infrastructure and enterprise open source companies, and backed by a leading Austin-based accelerator.This is an essential role on a small, sharp team, real ownership from day one, supporting every product the company builds, not one team's slice.

Responsibilities

Own reliability, availability, and performance of production systems, including GPU and model-serving infrastructureDefine and track SLOs/SLIs and error budgets, and lead incident response and blameless postmortemsDesign and maintain scalable infrastructure with Kubernetes, IaC, and CI/CD pipelinesBuild observability across the stack, metrics, logs, tracing, alertingOptimize cloud and GPU cost, capacity planning, and autoscaling for inference and training workloadsAutomate operational toil and improve deployment safety, canary releases, rollbacks, feature flagsWork with engineering teams on production readiness and system designThe ideal profile would have:6+ years in SRE, DevOps, or infrastructure engineering on large-scale distributed systemsDeep Kubernetes, containers, and at least one major cloud providerStrong IaC and automation skills, Terraform, Helm, Python or GoHands-on observability tooling, Prometheus, Grafana, Datadog, OpenTelemetryReal experience running on-call and leading incident response in high-traffic environmentsGenuine comfort with ambiguity and startup pace, this is not a big-company, process-heavy environmentBonus, not required:Experience with GPU clusters, ML model serving (vLLM, Triton, Ray), or high-throughput inference systemsWhat's in it for you:Real ownership over reliability and infrastructure, not a cog in a large SRE orgDirect influence on risk and best practices, without needing formal authority to give itSmall, tight-knit team that values working closely togetherGenuine startup pace, real trust to move fastThis role is not open to sponsorship at this time.Hubscale is an equal opportunity employer and does not discriminate on the basis of race, color, religion, sex, national origin, age, disability, or any other protected status.