Job Description:
Founded by pioneering journalists as the first social media newswire, Storyful was created out of the need to break the news faster and utilize social content to add context to reporting. Acquired by News Corp in 2013, Storyful has evolved into a premium service for media, business leaders and investors.
Our goal is to help our partners understand the attitudes, behaviors and emotions shaping the world. Powered by a unique ability to gather and streamline data from all corners of an increasingly complex information environment, our teams deliver clarity in a world of confusion. Our mission is to dig deeper into the nuance inherent in digital media to establish context, verify the truth and help our partners make sense of the world.
Storyful is building AI-native products on top of complex, high-volume, multi-source content. We are looking for a hands-on Senior QA Automation Engineer to raise the quality bar while increasing delivery speed through AI-augmented engineering.
This is a senior individual contributor role for someone who treats AI as a core part of their craft — using coding agents, LLMs, and evaluation frameworks to scale quality faster than headcount.
You will design and build the automation, evaluation, and quality foundations that enable engineers to own quality, while ensuring our products remain reliable, explainable, and trusted — even as they become increasingly probabilistic.
You will work closely with software engineers, data scientists, product managers, and SRE to embed quality into every stage of the development lifecycle.
What you will do
Design and build AI-augmented automation systems
Build and evolve scalable automation frameworks across web UI, APIs, and data pipelines (Playwright / TypeScript)
Use AI coding agents (e.g. Claude Code) to generate, refactor, and maintain test suites at scale
Translate natural-language acceptance criteria into executable, maintainable tests
Define reusable testing patterns that enable engineers to own automation within their domains
Continuously reduce flakiness using trace analysis, observability, and AI-assisted failure triage
Enable shift-left, engineering-led quality
Partner with engineers to embed testing early in the development lifecycle
Define pragmatic, risk-based test strategies across unit, integration, contract, and E2E layers
Establish clear definitions of done, quality gates, and release readiness standards
Build tooling and frameworks that allow teams to move fast without relying on central QA
Build QA practices for AI/LLM-powered features
Design evaluation pipelines for LLM-driven features using:
Golden datasets and regression harnesses
Semantic similarity scoring
LLM-as-a-judge evaluation patterns
Detect and prevent issues such as prompt drift, hallucinations, retrieval failures, and schema regressions
Test agentic workflows end-to-end (tool use, multi-step reasoning, failure modes)
Partner with data science to define measurable quality signals (precision, recall, grounding, drift)
Integrate quality into CI/CD and delivery
Embed automation and evaluation into CI/CD pipelines for fast, reliable feedback
Define and tune meaningful quality gates based on real metrics (not ceremony)
Support release processes with high-confidence signals and rollback readiness
Drive debugging, observability, and defect excellence
Investigate complex issues across distributed systems using logs, traces, and metrics
Improve observability, including LLM trace visibility (e.g. Langfuse)
Establish strong defect triage, categorisation, and reporting practices
Use data (leakage, flake rate, MTTR, escape rate) to continuously improve quality
Own non-functional and AI-specific risk testing
Embed security testing into automation (OWASP, API security, auth flows)
Test AI-specific risks (prompt injection, jailbreaks, unsafe tool use, data leakage)
Collaborate on performance, resilience, and scalability testing where it matters most
What good looks like in this…