5 hours ago
Seattle, WA, USASenior / Staff+
Base Salary
$140k - $220k/yr
Responsibilities
- Own the architecture for inference serving, GPU scheduling, Kubernetes operators, autoscaling, and dynamic capacity across cloud and customer-managed deployments.
- Design and calibrate evaluation systems for model, prompt, and agent changes, including golden datasets, LLM-as-judge pipelines, and regression gates.
- Advise on cost-aware model routing and cascading decisions across providers and model tiers.
- Apply physics-informed ML and enterprise AI expertise to client engagements and internal platform capabilities.
- Set technical standards for ML infrastructure and evaluation practices, mentor engineers, and maintain architectural coherence with inference platform, gateway, and evaluation teams.
Requirements
- At least 3 years of production-scale experience with ML infrastructure and inference serving, including vLLM, SGLang, TensorRT-LLM, or comparable systems.
- Strong experience with ML/LLM evaluation and reliability engineering, or the seniority to build the practice from scratch.
- Solid Kubernetes experience, ideally including GPU scheduling constraints, node pools, and autoscaling under GPU bottlenecks.
- Track record of senior- or staff-level technical leadership and setting technical direction.
- Research fluency through a PhD, publications, or equivalent depth is preferred but not required.
- Experience in startup and enterprise environments or in energy, real estate, utilities, climate, or related fields is a plus.
- Experience with PyTorch Lightning, JAX, HuggingFace, ONNX optimizations, C++, Rust, CUDA, Spark, Ray, Horovod, Dask, vector or graph databases, feature stores, or data lakes is advantageous.
- Strong collaboration, emotional intelligence, learning mindset, judgment under ambiguity, and ability to support others' success.
Benefits
- Competitive startup compensation based on capabilities, experience, and location, plus bonus eligibility and equity.
- Health insurance with meaningful dependent coverage and flexible paid time off.
- Fully remote work for candidates in the United States or Canada, with a Seattle-area teammate cluster.
- Travel to the Seattle area for the final interview, twice-yearly company summits, and approximately 10–20% onsite client work depending on location.
- Training and learning opportunities at a profitable, mission-driven, fast-growing company.
- Applicants must be authorized to work full-time in the United States; visa sponsorship is unavailable.
Tech Stack
Categories
About AZX
Tech transformation, societal shifts and environmental disruption put enormous pressure on critical industries like energy, infrastructure, real estate and others to adapt, pursue new growth opportunities and optimize operations. AZX was created to meet these challenges head-on. We deliver AI transformation for critical industries providing strategy, execution and acceleration solutions. We prioritize code over powerpoint, applying start-up principles to challenge conventional thinking and develop strategic AI technology and business solutions that can be implemented quickly. We are mission-driven and client-centric, solving hard problems and building value for people, organizations and the planet. We are AZX.