Senior Software Engineer – AI Inference & Runtime Platform

🕒 Agosto 31

☕ Washington – Remoto

☕ Washington – Remote

💵 $140.000 - $225.000 / ano

⏰ Tempo Integral

🟠 Sênior

🤖 Engenheiro de IA

👻 Score fantasma 0%

O que significa: quão provável esta vaga está aberta sem contratação ativa.Como ler: 60% ou mais significa que achamos que é uma vaga fantasma. Pontuações mais baixas preocupam menos.Como pontuamos: tempo em aberto, republicações, vagas abertas vs tamanho do time, rapidez para fechar vagas, e se o salário está divulgado.Observação: é uma estimativa de dados públicos, não um julgamento da empresa. Vagas reais podem ter pontuação alta, então use como uma dica, não como um fato.

Candidatar-se

Encontrar Vagas Remotas Similares

Configurar Alerta de Email para Novas Vagas

📊 Verifique sua pontuação de currículo para esta vaga

Melhore suas chances de conseguir uma entrevista verificando sua pontuação de currículo antes de se candidatar.

Enviar Currículo

AZX

SiteLinkedInTodas as Vagas

1 - 10 funcionários

Fundada em 2024

💼 Consultoria

📦 Logística

🏗️ Construção

Consulting • Logistics • Construction

A AZX é uma empresa de capital aberto que oferece soluções de IA especificamente adaptadas para as indústrias de energia, imobiliária e cadeia de suprimentos. Elas se concentram em resolver problemas dos clientes de forma rápida, aproveitando estratégias inovadoras e desenvolvendo soluções capacitadas por IA que proporcionam resultados mensuráveis. Com uma abordagem orientada por missões, a AZX enfatiza a criação de impacto tanto na eficiência organizacional quanto na sustentabilidade ambiental.

Descrição

• Own the inference control plane for open-weight models and custom task-model zoos across managed GPU clouds and customer-managed Kubernetes clusters • Manage serving-tier engine deployment and configuration, cold-start strategy, per-model SLOs, and upgrade/canary discipline • Administer the Kubernetes layer for inference and sandbox workloads, including operators, CRDs, autoscaling, GPU scheduling and sharing, and node lifecycle • Own the stateful data plane for hosted vector stores and graph stores, including deployment, backups, scaling, recovery, and tested restores • Oversee the sandbox runtime and host-side control plane, including lifecycle, exec, snapshot/fork, teardown, metering, and isolation-boundary threat modeling • Direct FastAPI control-plane services, Terraform/OpenTofu, Bicep, and dashboards • Run the platform layer supporting backend services and debug into backend services as needed • Manage the open-source posture through reviewed PRs, documentation, and reproducible builds • Build the fork engine, guest agent, and multi-substrate model lifecycle using Rust, Kubernetes controllers, and FastAPI endpoints • Account for per-token costs accurately, including client mid-stream disconnections • Operate hardware-isolated microVMs for secure, compliant execution of untrusted agent-generated code

🎯 Requisitos

• 5+ years of shipping production systems in a systems language • Rust is the house language; deep Go, C/C++, or Zig with genuine appetite for Rust counts • Familiarity with async runtimes, memory-safety discipline, and debugging at the syscall boundary • Experience operating Kubernetes workloads, including controllers or operators, scheduling, autoscaling, and node lifecycle • Ability to threat-model isolation boundaries, including namespaces, cgroups, seccomp, and hypervisors • Experience applying security best practices for agentic execution: least privilege, no credentials in the sandbox, audit trails, and human approval on write actions • Hands-on experience deploying or operating open-weight LLM serving infrastructure such as vLLM/SGLang or similar • Performance discipline in distributed systems • Practical depth in Rust (tokio), Python/FastAPI, Kubernetes operators, KEDA, Karpenter, GPU device plugins/DRA • Familiarity with Firecracker, Kata, gVisor, or comparable isolation technology • Familiarity with secrets management and egress control, such as Vault/KMS-class tools • Experience hosting stateful systems including vector stores and graph stores, with backup and failover discipline • Comfort operating across AWS/Azure/GCP and managed GPU clouds • Experience with Terraform/OpenTofu, Bicep, and OpenTelemetry • Bachelor's Degree; Master's is a plus • Must be currently authorized to work in the United States on a full-time basis • Must be able to travel 2x/year for company summits

🏖️ Benefícios

• Competitive early-stage startup compensation (based on capabilities, experience, and location) • Bonus eligibility • Health insurance with meaningful coverage for dependents • Flexible paid time off • Equity • Fully remote culture with a cluster of teammates in Seattle • Company summits 2x/year