SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
AiDASH is a climate-tech platform that uses satellite imagery and geospatial data to help electric utilities manage grid resilience through vegetation, asset, storm, and wildfire intelligence. The company serves over 200 customers and has been recognized by Forbes, TIME, and Deloitte for innovation in green technology.
As an SDET 3 (Senior Development Engineer in Test) on the Platform ML team, you will own end-to-end quality assurance for machine learning models that process satellite imagery, geospatial data, and weather data. Your role spans from training data preparation through inference pipelines to production-scale performance validation. You will validate both functional correctness and scaling behavior, and leverage agentic AI tools (Cursor, Claude) to accelerate test design and automation while maintaining engineering rigor.
Key responsibilities:
• Build and maintain validation frameworks for computer vision models, particularly satellite and geospatial models. Catch regressions in accuracy, precision/recall, and IoU before production.
• Design version-aware model regression pipelines that compare inference outputs across model versions on curated golden datasets, providing clear go/no-go signals for every release.
• Establish data quality as a first-class gate by validating training and evaluation datasets for label quality, class balance, geographic and seasonal coverage, data leakage, and drift.
• Design and execute load and benchmark tests for inference services and batch pipelines on AWS and Kubernetes, identifying throughput, latency, and cost limits before customers encounter them.
• Automate API, contract, and data-pipeline tests across distributed services. Use logs, metrics, and traces to accelerate root-cause analysis.
• Strengthen shared automation frameworks and establish standards for maintainable, non-flaky tests. Demonstrate how agentic AI tools can speed up test authoring, triage, and reporting under human review.
• Influence release decisions through high-visibility quality signals that directly shape what ships across AiDASH's product lines.
Requirements:
• 7+ years of QA/test automation experience, with deep backend automation expertise.
• Proven experience validating ML models and backend systems end-to-end.
• Strong proficiency in Python and at least one other programming language (Java, Go, C++, Rust, or similar).
• Hands-on experience with test frameworks (pytest, unittest, TestNG, or equivalent).
• Demonstrated expertise in API testing (REST, gRPC, or similar).
• Experience with CI/CD pipelines (Jenkins, GitHub Actions, Bitbucket Pipelines, or equivalent): triggering suites, reading failures, improving pipeline reliability.
• Experience with performance testing tools (JMeter, k6, Locust, or equivalent): load/benchmark basics, interpreting results, flagging SLA/risk.
• Exposure to agentic development tools such as Cursor and Claude (or similar) for coding, test authoring, log/triage assistance, and documentation, used with human review and quality gates.
• Nice-to-have: experience with computer vision models, satellite/geospatial data, or ML validation frameworks; familiarity with Kubernetes, AWS, or distributed systems; understanding of ML health concepts.
