Sr. SDET
Core
Own test automation and quality frameworks for Dialpad's AI Voice Agent services, covering end-to-end product experiences from UI to APIs and audio/text interactions.
Role type
Senior SDET specializing in AI/LLM quality engineering
Builds
Automated test infrastructure, evaluation frameworks, and CI/CD integrations for agentic AI workflows
Domain
AI/LLM business communications platform
Deliverable
production ML models | product features
Required skills
Python, Java, JavaScript, distributed cloud-native SaaS testing, LLM/AI agent testing, probabilistic testing, test framework design, CI/CD pipelines, LLM observability, performance/load testing, AI evaluation techniques
Preferred skills
Prompt engineering, model selection, human-in-the-loop validation, Kubernetes, Google Cloud Platform, React, Vue3, LiveKit
Technologies
Python, Java, JavaScript, Kubernetes, Google Cloud Platform, Cloud Run, App Engine, Datastore, Redis, ElasticSearch, Vue3, React, LiveKit, LLM APIs, Jenkins, GitHub Actions
Responsibilities
Own end-to-end quality for agentic features and workflows; Design and build automation tooling for AI/LLM-driven systems; Develop and maintain evaluation frameworks to measure response quality; Drive automation coverage using deterministic and probabilistic validation; Integrate AI quality checks into CI/CD pipelines; Build tooling for LLM observability and debugging; Partner with Applied AI teams on prompt engineering and evaluation strategies; Design and execute performance and load tests for AI services; Identify and mitigate risks related to hallucinations, bias, and safety; Define and track AI quality KPIs; Participate in design and architecture reviews; Mentor engineers on AI quality engineering practices
Seniority
Senior, hands-on IC