Staff Software Development Test Engineer

Responsibilities

• Own end-to-end quality for AI platform capabilities, including feature pipelines, training/serving infrastructure, model registry, and LLM gateways.
• Design and implement automated testing frameworks for platform APIs, SDKs, services, and infrastructure components.
• Validate the correctness, completeness, and consistency of features and model inputs/outputs throughout the ML lifecycle.
• Test model-serving and inference services for latency, throughput, scalability, and reliability under load.
• Build regression and reconciliation suites for large-scale platform changes, migrations, and version upgrades.
• Define quality metrics and SLO validation, utilizing automated monitoring to detect platform anomalies.
• Use AI and LLMs to accelerate quality engineering through test generation and synthetic data creation.
• Drive root cause analysis for production platform issues and partner with engineering teams on preventive improvements.

Requirements

• 8+ years in SDET, quality engineering, or software engineering, with experience building automation frameworks for backend services or infrastructure.
• Strong programming skills in Python and/or Java/Go.
• Experience testing distributed systems, APIs, data pipelines, or ML/data platforms.
• Solid understanding of ML lifecycle components such as feature stores, training/serving, and model deployment.
• Experience with performance, load, and scalability testing.
• Familiarity with CI/CD, Docker, Kubernetes, and cloud environments (AWS/GCP/Azure).
• Understanding of LLM/ML failure modes and evaluation concepts.

Preferred Qualifications

• Experience with ML platform tools like MLflow, Feast, KServe, Ray, or Kubeflow.
• Experience with LLM infrastructure, including vLLM, model gateways, or vector databases (Milvus/Pinecone).
• Experience with observability stacks such as Prometheus, Grafana, or Datadog.
• Experience testing multi-tenant, high-throughput SaaS platforms.
• Exposure to chaos or reliability engineering.

About the Company

Tekion is positively disrupting the automotive industry with the first cloud-native automotive platform. By leveraging cutting-edge technology, big data, machine learning, and AI, Tekion connects the entire automotive retail ecosystem through a seamless platform that serves OEMs, retailers, and consumers globally.