Skip to main content
Loading
loadingbar
Loading, Please wait..!!

Senior Software Engineer (AI Inference & Runtime Platform)

  • Senior Software Engineer (AI Inference & Runtime Platform) job type Posted on: Nov 19, 2026
  • Senior Software Engineer (AI Inference & Runtime Platform) experience level Provn
  • Senior Software Engineer (AI Inference & Runtime Platform) employment type Seattle, Washington
  • Senior Software Engineer (AI Inference & Runtime Platform) salary Salary: $140,000 per year
  • Senior Software Engineer (AI Inference & Runtime Platform) employment type Remote
  • Senior Software Engineer (AI Inference & Runtime Platform) salary Full-time

Point Apply Here APPLY LATER

Curious about compensation?

Explore the historical salary trends, average pay, and estimated compensation for Senior Software Engineer (AI Inference & Runtime Platform) roles in Washington.

View Salary Guide →

Job Title :

Senior Software Engineer (AI Inference & Runtime Platform)

Job Type :

Full-Time

Job Location :

Seattle Washington United States

Remote :

Yes

Jobcon Logo Job Description :

Job DescriptionJob DescriptionSenior Software Engineer (AI Inference & Runtime Platform) \nAZX | Remote (U.S.) | Full time | Applications close November 12\nCompensation: $140,000 - $230,000, plus bonus eligibility and equity\nYou will own the layer where AI work physically happens: the machines, the isolation boundary, and the models running on them. This role anchors on two systems.\nThe first is our inference control plane: open-weight models and custom task-model zoos, hosted and operated across managed GPU clouds and customer-managed Kubernetes clusters, with scale-to-zero economics, cold-start discipline, and per-token cost accounting that stays correct even when a client disconnects mid-stream, along with the Kubernetes layer those workloads live on (operators, autoscaling, node lifecycle).\nThe second is our agent-sandboxing platform: hardware-isolated microVMs for running untrusted, agent-generated code securely and compliantly by construction, where agents operate with least privilege, never see a credential, and a human gates anything that writes to a system of record.\nYou'll write Rust in the morning, a Kubernetes controller after lunch, and a FastAPI control-plane endpoint before you go home, building the fork engine, the guest agent, and the multi-substrate model lifecycle. We're looking for people who've built this class of stack (an inference-serving or serverless-GPU platform), operated it hard at scale, or ideally both. About AZX \nOur mission is to accelerate positive impact in critical industries through AI transformation. We specialize in physics-informed ML and enterprise AI solutions that directly address climate and sustainability challenges.\nWe're growing quickly and already work with category leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe), and utilities.\nWe bootstrapped profitably for our first year and are now backed by leading investors focused on AI, climate, and energy.\nWe work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics. We're building our company for long-term success and aim to create the ultimate place to work for those passionate about AI and making a positive impact. What You'll Work On \n\n Manage the serving tier for open-weight models: engine deployment and configuration, cold-start strategy, per-model SLOs, and upgrade/canary discipline\n Administer the Kubernetes layer for inference and sandbox workloads: operators and CRDs, autoscaling (KEDA/Karpenter-class), GPU scheduling and sharing, and node lifecycle\n Own the stateful data plane end to end with restore procedures that are regularly tested\n Oversee the sandbox runtime and its host-side control plane: lifecycle, exec, snapshot/fork, teardown, metering, and the threat model of the isolation boundary\n Direct the FastAPI control-plane services, Terraform/OpenTofu, Bicep, and the dashboards\n Run the layer the backend services team builds on, expect to debug into their services, and expect them to read your dashboards\n Manage the open-source posture: build to OSS standards and release as it matures, with reviewed PRs, real docs, and reproducible builds\n What We're Looking For \nIf this job sounds like a great fit but you don't check all of these boxes, we'd still love to hear from you.\n\n 5+ years of shipping production systems in a systems language. Rust is the house language, but polyglots are welcome: deep Go, C/C++, or Zig with genuine appetite for Rust counts. Async runtimes, memory-safety discipline, and debugging at the syscall boundary should be familiar territory\n You've operated Kubernetes workloads that other people depended on: controllers or operators, scheduling, autoscaling, node lifecycle. You've been paged, and the experience changed how you build\n Strong ability to threat-model isolation boundaries (namespaces, cgroups, seccomp, hypervisors), including identifying what an untrusted guest could observe, forge, or exhaust, and applying security best practices for agentic execution: least privilege, no credentials in the sandbox, audit trails, and human approval on write actions\n Hands-on experience deploying or operating open-weight LLM serving infrastructure (vLLM/SGLang or similar), including packaging models into reliable, metered production endpoints\n Performance discipline in distributed systems: you measure before you optimize, and you can tell the story of a latency you killed with the numbers attached\n Practical depth in some of our core stack: Rust (tokio), Python/FastAPI, Kubernetes operators (controller-runtime/Kubebuilder/CRDs), KEDA, Karpenter, GPU device plugins/DRA, with a genuine willingness to research your way into the rest\n Familiarity with isolation technology (Firecracker, Kata, gVisor, or comparable), secrets management and egress control (Vault/KMS-class), and hosting stateful systems (vector stores like pgvector/Qdrant, graph stores like Neo4j) with backup and failover discipline\n Comfort operating across cloud and GPU substrates (AWS/Azure/GCP plus managed GPU clouds) using infrastructure-as-code (Terraform/OpenTofu, Bicep) and observability tooling (OpenTelemetry)\n Bachelor's degree\n Nice to Have \n\n Master's degree\n Location \nThis role is fully remote within the U.S., with a cluster of teammates in Seattle. You'll travel twice a year for company summits. Candidates must be currently authorized to work in the U.S. on a full-time basis. AZX is unable to sponsor or take over sponsorship of employment visas at this time. Hiring Process \nProvn is our hiring partner.\nOur interview process includes a written take-home assignment followed by a live two-hour technical session with our engineering team, so if that format isn't a good fit, we'd ask that you not apply.\nPlease apply to no more than two AZX roles at a time. Anyone who applies to more than two roles within a six-month period will be automatically disqualified.\nProvn is your proof layer for getting hired. Builders complete challenges for AI-transformed roles to show AI fluency and showcase critical skill requirements. Hiring managers and recruiters are saying that candidate video presentations are more helpful than referrals for selecting their interview loops. Benefits & Perks \n\n Be part of a fast-growing, profitable, mission-driven company with industry-leading clients tackling the massive opportunity of AI transformation in critical industries\n Competitive early-stage startup compensation (based on capabilities, experience, and location)\n Bonus eligibility\n Health insurance with meaningful coverage for dependents\n Flexible paid time off\n Equity\n Fully remote culture with a cluster of teammates in Seattle\n\nAZX is an equal opportunity employer. We are committed to building a diverse and inclusive team and do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, or any other characteristic protected by applicable law.

Jobcon Logo Position Details

Posted:

Nov 19, 2026

Reference Number:

16275_beba35d5

Employment:

Full-time

Salary:

$140,000 per year

City:

Seattle

Job Origin:

APPCAST_CPC

Share this job:

  • linkedin

Jobcon Logo
A job sourcing event
In Dallas Fort Worth
Aug 19, 2017 9am-6pm
All job seekers welcome!

Senior Software Engineer (AI Inference & Runtime Platform)    Apply

Click on the below icons to share this job to Linkedin, Twitter!

Job DescriptionJob DescriptionSenior Software Engineer (AI Inference & Runtime Platform) \nAZX | Remote (U.S.) | Full time | Applications close November 12\nCompensation: $140,000 - $230,000, plus bonus eligibility and equity\nYou will own the layer where AI work physically happens: the machines, the isolation boundary, and the models running on them. This role anchors on two systems.\nThe first is our inference control plane: open-weight models and custom task-model zoos, hosted and operated across managed GPU clouds and customer-managed Kubernetes clusters, with scale-to-zero economics, cold-start discipline, and per-token cost accounting that stays correct even when a client disconnects mid-stream, along with the Kubernetes layer those workloads live on (operators, autoscaling, node lifecycle).\nThe second is our agent-sandboxing platform: hardware-isolated microVMs for running untrusted, agent-generated code securely and compliantly by construction, where agents operate with least privilege, never see a credential, and a human gates anything that writes to a system of record.\nYou'll write Rust in the morning, a Kubernetes controller after lunch, and a FastAPI control-plane endpoint before you go home, building the fork engine, the guest agent, and the multi-substrate model lifecycle. We're looking for people who've built this class of stack (an inference-serving or serverless-GPU platform), operated it hard at scale, or ideally both. About AZX \nOur mission is to accelerate positive impact in critical industries through AI transformation. We specialize in physics-informed ML and enterprise AI solutions that directly address climate and sustainability challenges.\nWe're growing quickly and already work with category leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe), and utilities.\nWe bootstrapped profitably for our first year and are now backed by leading investors focused on AI, climate, and energy.\nWe work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics. We're building our company for long-term success and aim to create the ultimate place to work for those passionate about AI and making a positive impact. What You'll Work On \n\n Manage the serving tier for open-weight models: engine deployment and configuration, cold-start strategy, per-model SLOs, and upgrade/canary discipline\n Administer the Kubernetes layer for inference and sandbox workloads: operators and CRDs, autoscaling (KEDA/Karpenter-class), GPU scheduling and sharing, and node lifecycle\n Own the stateful data plane end to end with restore procedures that are regularly tested\n Oversee the sandbox runtime and its host-side control plane: lifecycle, exec, snapshot/fork, teardown, metering, and the threat model of the isolation boundary\n Direct the FastAPI control-plane services, Terraform/OpenTofu, Bicep, and the dashboards\n Run the layer the backend services team builds on, expect to debug into their services, and expect them to read your dashboards\n Manage the open-source posture: build to OSS standards and release as it matures, with reviewed PRs, real docs, and reproducible builds\n What We're Looking For \nIf this job sounds like a great fit but you don't check all of these boxes, we'd still love to hear from you.\n\n 5+ years of shipping production systems in a systems language. Rust is the house language, but polyglots are welcome: deep Go, C/C++, or Zig with genuine appetite for Rust counts. Async runtimes, memory-safety discipline, and debugging at the syscall boundary should be familiar territory\n You've operated Kubernetes workloads that other people depended on: controllers or operators, scheduling, autoscaling, node lifecycle. You've been paged, and the experience changed how you build\n Strong ability to threat-model isolation boundaries (namespaces, cgroups, seccomp, hypervisors), including identifying what an untrusted guest could observe, forge, or exhaust, and applying security best practices for agentic execution: least privilege, no credentials in the sandbox, audit trails, and human approval on write actions\n Hands-on experience deploying or operating open-weight LLM serving infrastructure (vLLM/SGLang or similar), including packaging models into reliable, metered production endpoints\n Performance discipline in distributed systems: you measure before you optimize, and you can tell the story of a latency you killed with the numbers attached\n Practical depth in some of our core stack: Rust (tokio), Python/FastAPI, Kubernetes operators (controller-runtime/Kubebuilder/CRDs), KEDA, Karpenter, GPU device plugins/DRA, with a genuine willingness to research your way into the rest\n Familiarity with isolation technology (Firecracker, Kata, gVisor, or comparable), secrets management and egress control (Vault/KMS-class), and hosting stateful systems (vector stores like pgvector/Qdrant, graph stores like Neo4j) with backup and failover discipline\n Comfort operating across cloud and GPU substrates (AWS/Azure/GCP plus managed GPU clouds) using infrastructure-as-code (Terraform/OpenTofu, Bicep) and observability tooling (OpenTelemetry)\n Bachelor's degree\n Nice to Have \n\n Master's degree\n Location \nThis role is fully remote within the U.S., with a cluster of teammates in Seattle. You'll travel twice a year for company summits. Candidates must be currently authorized to work in the U.S. on a full-time basis. AZX is unable to sponsor or take over sponsorship of employment visas at this time. Hiring Process \nProvn is our hiring partner.\nOur interview process includes a written take-home assignment followed by a live two-hour technical session with our engineering team, so if that format isn't a good fit, we'd ask that you not apply.\nPlease apply to no more than two AZX roles at a time. Anyone who applies to more than two roles within a six-month period will be automatically disqualified.\nProvn is your proof layer for getting hired. Builders complete challenges for AI-transformed roles to show AI fluency and showcase critical skill requirements. Hiring managers and recruiters are saying that candidate video presentations are more helpful than referrals for selecting their interview loops. Benefits & Perks \n\n Be part of a fast-growing, profitable, mission-driven company with industry-leading clients tackling the massive opportunity of AI transformation in critical industries\n Competitive early-stage startup compensation (based on capabilities, experience, and location)\n Bonus eligibility\n Health insurance with meaningful coverage for dependents\n Flexible paid time off\n Equity\n Fully remote culture with a cluster of teammates in Seattle\n\nAZX is an equal opportunity employer. We are committed to building a diverse and inclusive team and do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, or any other characteristic protected by applicable law.

Loading
Please wait..!!