SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: CAD 151,000 - 175,000 / annual
Dialpad is an AI platform for customer experience that enables AI agents to resolve customer problems in real time across voice and digital channels. The company's AI agents learn from human agents and improve with every interaction, helping organizations deliver better experiences and increase operational efficiency.
As a Senior Software Development Engineer in Test (SDET) in Agentic QA, you will own the test automation and quality frameworks supporting Dialpad's AI Voice Agent services. You will develop automated tests for end-to-end product experiences spanning frontend UI, backend services, APIs, and audio/text interactions. Your work will cover orchestration flows, agent configuration experiences, and guardian safeguards to create robust automated coverage for functionality, performance, reliability, and UX.
Key responsibilities include:
- Own end-to-end quality for agentic features and workflows, including strategy, development, execution, and release qualification
- Design and build automation tooling and frameworks for AI/LLM-driven systems, including prompt flows, agent orchestration, and tool integrations
- Develop and maintain evaluation frameworks (evals) to measure response quality, accuracy, and hallucination rates
- Drive automation coverage (80%+ for critical AI workflows) using deterministic and probabilistic validation approaches
- Integrate AI quality checks into CI/CD pipelines with fast feedback cycles (<15 minutes for PR validation)
- Build tooling for LLM observability and debugging, including prompt tracing and response analysis
- Partner with Applied AI teams on prompt engineering, model selection, and evaluation strategies
- Design and execute performance and load tests for AI services (latency, throughput, cost efficiency)
- Identify and mitigate risks related to hallucinations, bias, safety, and edge cases
- Define and track AI quality KPIs (task success rates, precision/recall, latency, etc.)
- Participate in design and architecture reviews to ensure systems are testable, observable, and resilient
- Mentor engineers and contribute to raising the bar on AI quality engineering practices
You will develop substantial amounts of automated test infrastructure and partner deeply with the development team to make the fast-growing AI platform more testable, stable, and delightful for customers. This position is based at one of Dialpad's Canadian offices and reports to a QA Engineering Manager in the United States.
Requirements:
- 6+ years of experience in software engineering or SDET roles with emphasis on software development
- Strong programming skills in Python (preferred), Java, or JavaScript
- Experience testing distributed, cloud-native SaaS systems and APIs
- Demonstrated proficiency in coding with AI agents to accelerate development and improve code quality
- Hands-on exposure to LLMs or AI/ML systems (e.g., OpenAI, Claude, Gemini, or similar platforms)
- Understanding of non-deterministic systems and probabilistic testing approaches
- Experience building test frameworks and scalable automation systems
- Familiarity with AI evaluation techniques (benchmarking, golden datasets, human-in-the-loop validation)
- Experience with CI/CD pipelines (e.g., Jenkins, GitHub Actions)
- Strong collaboration skills with ability to work across distributed teams and time zones
- Bachelor's degree in Computer Science or equivalent practical experience
- Backend experience with: Python, Go, Google Cloud Platform, Cloud Run/App Engine, Kubernetes, Datastore, Redis, ElasticSearch
- Frontend experience with: Vue3, React
- AI Stack experience with: LLM APIs, LiveKit, prompt orchestration frameworks, evaluation tooling
