Systems Engineer (AI Infrastructure)

Location: Remote within the United States; applicants must be currently authorized to work in the United States on a full-time basis. Travel to company summits twice per year is required.

Compensation: $140K–$225K annually, plus equity and bonus eligibility.

Company

hirify.global is a public benefit corporation building physics-informed machine learning and enterprise AI solutions for climate, sustainability, energy, real estate, logistics, and utilities.

What you will do

• Manage open-weight model serving, including deployments, configuration, cold-start strategies, service-level objectives, upgrades, and canary releases.
• Administer Kubernetes infrastructure for inference and sandbox workloads, including operators, CRDs, autoscaling, GPU scheduling, and node lifecycle management.
• Operate vector and graph data stores with tested backup, restore, scaling, and failover procedures.
• Own the secure sandbox runtime and host-side control plane for lifecycle management, execution, snapshots, forking, teardown, metering, and threat modeling.
• Build and direct FastAPI control-plane services, infrastructure-as-code, and observability dashboards while debugging across backend services.
• Maintain open-source engineering standards through reviewed pull requests, documentation, and reproducible builds.

Requirements

• At least five years of shipping production systems in a systems language; Rust is preferred, with deep Go, C/C++, or Zig experience also considered.
• Production experience operating Kubernetes workloads, including controllers or operators, scheduling, autoscaling, and node lifecycle management.
• Strong threat-modeling skills for isolation boundaries, including namespaces, cgroups, seccomp, hypervisors, least privilege, credential protection, audit trails, and human approval for system-of-record writes.
• Hands-on experience deploying or operating open-weight LLM serving infrastructure such as vLLM or SGLang in reliable, metered production endpoints.
• Practical experience with Rust and Tokio, Python and FastAPI, Kubernetes operators, KEDA, Karpenter, GPU device plugins or DRA, distributed-systems performance, and observability.
• Current United States work authorization is required; visa sponsorship is not available. A bachelor's degree is required.

Nice to have

• Experience with Firecracker, Kata, gVisor, or comparable isolation technologies.
• Familiarity with Vault or KMS-class secrets management and egress control.
• Experience operating pgvector, Qdrant, Neo4j, or comparable stateful vector and graph systems.
• Master's degree.

Culture & Benefits

• Fast-growing, profitable, mission-driven startup focused on AI transformation in critical industries.
• Fully remote culture with a cluster of teammates in Seattle.
• Health insurance with dependent coverage.
• Flexible paid time off, equity, and bonus eligibility.
• Opportunities to build and release infrastructure according to open-source standards.

Hiring process

• Applicants should apply to no more than two roles within a six-month period.
• Candidates who do not meet every qualification are still encouraged to apply.