Software Engineer (Backend-Focused) About the RoleWe're looking for a Staff or Senior ML Engineer to own the technical backbone of how AZX serves and evaluates models at scale. This is a high-leverage IC role spanning our inference platform - GPU scheduling, autoscaling, and serving infrastructure for vLLM/SGLang across cloud and customer-managed clusters - and the evaluation systems that tell us whether model, prompt, and agent changes that make things better.
You'll create technical direction for how AZX serves models reliably. This role suits someone who wants architectural ownership over hard ML infrastructure problems, paired with the judgment to build the guardrails that let the rest of the team move fast safely.
What you will doYou will work on software projects in client engagements, and over time, internal platform capabilities.
You will:
- Build and maintain backend services for our LLM gateway - routing, rate limiting, key management, and observability in front of the inference fleet.
- Contribute to sandboxing and isolation infrastructure that keeps agent-generated code safe to execute, working alongside our security-focused engineers.
- Support Kubernetes-based platform services, including operators and autoscaling logic adjacent to our inference platform.
- Write high-performance backend code in Go, Rust, or async Python (FastAPI/Starlette), working with infrastructure like Envoy and gRPC.
- Instrument services with OpenTelemetry so behavior, latency, and cost stay observable as the platform scales.
- Collaborate across the gateway, sandbox, and inference platform teams, flexing across areas as priorities shift.
Core Qualifications - Technical and foundational- 4+ years of experience in backend engineering fundamentals: distributed systems, API design, and production experience in Go, Rust, or async Python.
- Familiarity with LLM-specific backend concerns (rate limiting, caching, token accounting) is a plus, though not required on day one.
- Exposure to Kubernetes and containerization; interest in sandboxing or security is a plus.
- Comfort working across a range of platform concerns rather than one narrow specialty - this role is intentionally broader than our specialist infra profiles.
- Eagerness to grow into deeper specialization in gateway, sandbox, or inference infrastructure over time.
Values and Culture Qualifications- High emotional intelligence and a learning mindset
- Strong collaboration skills
- Enjoy others' success and a fun, positive environment.
- Comfortable making decisions in the face of ambiguity and course correcting as needed.
Bonus Qualifications (not required but a huge plus)- Experience in both startup and enterprise environments
- Past work in energy, real estate, utilities, climate or related fields
- Bonus if you have experience and passion in one or more of
- Additional web frameworks (e.g. Svelte, Vue, Angular)
- Lower-level languages e.g. C++, Rust
- Networking paradigms e.g. GraphQL, Websockets
- ML capabilities e.g. Sk-learn, xgboost, Pytorch/Tensorflow/JAX, Onnx...
- Additional database types such as graph or vector databases
- DevOps e.g. CI/CD pipelines, Docker, Kubernetes, Terraform, Pulumi and/or Bicep
- Generative AI e.g. prompt engineering, RAG, fine-tuning, tooling ecosystem
Compensation & benefits- 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
- Training and learning opportunities
- Be part of a fast-growing, profitable, mission-driven company with industry leading clients tackling the massive opportunity of AI transformation in critical industries
Logistics- Remote but only USA/Canada
- Must be willing to travel to Seattle area for final interview and travel 2x/year for company summits
Next stepsIf this job sounds great, we'd love to hear from you. If you feel aligned to the company but don't check all these boxes, we'd still love to hear from you!
