Northline Intelligence
Staff AI Platform Engineer — LLM & Model Operations
Remote within the United States

Northline Intelligence helps operational teams use language models in high-consequence workflows. We need a Staff AI Platform Engineer to build the paved road from experimentation to observable production.

Responsibilities
- Design Python services and SDKs for evaluation, registration, deployment, routing, and monitoring.
- Build Kubernetes inference and batch workloads across GPU and CPU capacity.
- Establish offline and online evaluation contracts for quality, safety, latency, structured output, and cost.
- Own traces, model and prompt lineage, SLOs, drift signals, and incident diagnostics.
- Make the correct path the easiest path for scientists and product engineers.
- Lead RFCs and cross-team technical decisions.
- Improve economics through caching, batching, routing, and model selection.

Requirements
- 8+ years in software engineering with significant Python depth.
- 3+ years building AI infrastructure used by multiple teams.
- Production Kubernetes, cloud, CI/CD, IaC, and distributed-systems experience.
- Hands-on LLM evaluation, serving, observability, and debugging.
- Strong written design communication and a record of platform adoption.

Preferred: MLflow, OpenTelemetry, vector retrieval, GPU scheduling, model gateways, Rust or Go.

This company and posting are fictional and were created for a JobFitIQ demonstration.