Staff Software Development Test Engineer
Core
Build confidence in the quality, reliability, and performance of Tekion's AI Platform infrastructure, including model training/serving, feature pipelines, and LLM gateways.
Role type
Staff Software Development Test Engineer (AI Platform)
Builds
AI platform infrastructure, model training/serving tooling, feature pipelines, and LLM gateways
Domain
Artificial Intelligence / Machine Learning Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Python, Java/Go, distributed systems testing, ML lifecycle components, performance/load testing, CI/CD, containers, cloud platforms, debugging, root cause analysis
Preferred skills
ML platform tools (MLflow, Feast, KServe, Ray), observability stacks (Prometheus, Grafana), multi-tenant SaaS testing, chaos engineering
Technologies
Python, Java, Go, Docker, Kubernetes, AWS, GCP, Azure, MLflow, Feast, KServe, Ray, Kubeflow, SageMaker, Vertex AI, vLLM, Milvus, Pinecone, Prometheus, Grafana, Datadog
Responsibilities
Design and implement automated testing frameworks for platform APIs, SDKs, and infrastructure; Validate model-serving correctness, feature integrity, and system reliability under load; Build regression and reconciliation suites for large-scale platform changes; Define quality metrics and SLO validation with automated monitoring; Use AI/LLMs to accelerate test generation and automation; Drive root cause analysis for production issues.
Seniority
Staff, hands-on IC with strategic influence