• Design, build, and deploy scalable Generative AI platforms and applications. • Develop AI solutions leveraging AI Agents, RAG pipelines, and/or Knowledge Graph architectures. • Write clean, scalable, production-quality code using Python or Java. • Own end-to-end platform development and deployment within a DevOps environment. • Implement and maintain CI/CD pipelines using GitHub Actions and/or Jenkins. • Develop and manage Infrastructure as Code (IaC) using Terraform. • Deploy and manage solutions on AWS serverless services and/or Kubernetes-based infrastructure. • Collaborate with cross-functional teams to improve platform scalability, reliability, performance, and security. • Monitor, troubleshoot, and optimize AI platform operations in production environments. • Stay current with emerging AI technologies and recommend platform improvements and best practices.

• Architect and implement the MLOps strategy for the program • Design and own enterprise-grade ML/LLM pipelines • Build container-oriented ML platforms (GKE-first) • Implement hybrid MLOps + LLMOps workflows • Serve as a technical authority across multiple internal and customer projects • Enable observability, monitoring, drift detection, lineage tracking, and auditability across ML/LLM systems • Collaborate with cross-functional teams to deliver production-ready ML solutions • Ensure all solutions adhere to security, governance, and compliance expectations • Conduct architecture reviews, troubleshoot complex ML system issues, and guide teams through implementation • Mentor engineers and provide guidance on modern MLOps tools

Role Description You'll design and own the scalable, low-latency infrastructure that powers uRun's real-time inference runtime, the platform that makes live, interactive, multi-user AI workloads possible. - This is not classic ops or cloud management; you'll be deep in the AI runtime itself. - Latency, frame rate, and interactive quality of service are first-class platform properties. - The workloads are GPU-constrained, memory-bound, and bursty. - You will often write platform features, custom controllers, and scaling logic. - You will report directly to our founder, Keegan McCallum, and set the technical direction for the engineering organization. Qualifications - 7+ years as an engineer, with a proven track record architecting and owning large-scale production systems. - Deep Kubernetes expertise, including GPU-heavy clusters (NVIDIA tooling, autoscaling on GPU nodes) and service-mesh patterns. - Strong cloud and infrastructure-as-code experience: AWS, GCP, or Azure; Terraform, Pulumi, or equivalent; networking and security (VPC, IAM, API-gateway-style routing). - SRE-style thinking and observability depth: Prometheus/Grafana, OpenTelemetry, distributed tracing, SLOs, incident response, and post-mortems. - Proficiency in at least one of Python, Go, or TypeScript/Node.js for platform tooling, automation, and glue code. - Experience with streaming or real-time systems: WebRTC, low-latency video pipelines, or comparable latency-sensitive workloads. - A track record of mentoring engineers and influencing cross-functional teams. Requirements - Hands-on experience with GPU-constrained, memory-bound, or bursty workloads. - Experience writing custom Kubernetes controllers, scaling logic, or other platform features in-house. - Early-stage startup experience: owning ambiguous problems end-to-end and setting technical direction with limited scaffolding. Benefits - Competitive salary and meaningful equity in an early-stage AI infrastructure company. - Health, dental, and vision — full coverage. - 401(k) — company-supported retirement savings. - FSA/HSA — flexible spending accounts for healthcare costs. - Paid time off — we trust you to manage your time. - Top-tier tooling — access to the best AI tools available: Claude, Codex, Kimi, and whatever else helps you move faster. - MacBook Pro and AirPods — the hardware you need, on us. Company Description We build the stage, not the show. We're an infrastructure company, a developer-tools company, and a production partner for model labs, and focus is a deliberate choice we've made and hold to. - Day-to-day, that means a small team, a high bar, and real ownership. - You won't wait for permission or inherit a backlog of someone else's decisions. - In a founding security role, the function is what you make it. - It also means ambiguity: priorities shift, not everything is documented. - You'll often be the person who decides what "secure enough, for now" means.

• Own and scale build automation — design, build, and maintain our CI/CD infrastructure (pipelines, runners, artifact storage, signing agents, self-hosted macOS runners); ensure developers across backend, frontend, and mobile can iterate quickly without worrying about builds breaking down • Take charge of our mobile pipelines, with particular focus on iOS: automate versioning, provisioning profile management, keychain handling, automated signing, .ipa generation, TestFlight distribution, and App Store submission via Fastlane or native tooling • Embed quality and traceability into build stages — integrate linting, on-device tests (XCTest, Espresso, Appium), code coverage metrics, and build-state dashboards to reduce flakiness and turnaround time • Apply an SRE mindset to delivery — model build success/failure ratios as SLIs, define error budgets, track pipeline latency (time to green), and build alerts so broken builds are fixed within minutes • Automate for speed and reliability — build caching, parallel job orchestration, staging environment mirroring (via Terraform), and fast rollback workflows so every pipeline is idempotent and traceable. • Champion cross-team collaboration — coach developers on writing reliable Makefile/Gradle/Xcode configurations, secure signing practices, and branching models. • Lead incident response for build failure — serve on rotational pager for CI systems, drive blameless post-mortems, and automate resilient fallback logic (e.g. fallback runners, sourced caching). • Strategize adoption of next-gen tools — evaluate options like GitHub’s macOS runners, Bamboo, Bitrise, or Codemagic to support future iOS scale and cross-platform parity.