AI QA Engineer
Descripción del puesto:
AI QA Engineer Job Description
About Us
We are a tech company with a business-driven DNA, founded in Barcelona, with the vision of becoming a global leader in the creation of digital hubs for major corporations worldwide.
At our hub, we dont just build digital products we help shape the digital business strategy behind them. Our teams operate at the intersection of technology and business, acting as high-level strategic partners for the companies we work with. Were trusted not only to deliver, but to lead driving innovation, challenging assumptions, and defining the future of digital for global organizations.
We work with agile methodologies, embracing continuous iteration as our mantra. Our multidisciplinary teams manage the entire end-to-end lifecycle of our digital products, and we are dynamic and business oriented.
Job Summary
We are looking for an AI QA Engineer to join our AI for Coding Team, ensuring the reliability and quality of both human and AI-generated code.
This role blends traditional QA excellence with advanced AI evaluation designing regression frameworks, validating AI-generated pull requests, and defining benchmarks for AI model performance. Youll collaborate with developers and ML engineers to ensure every release meets quality standards and measurable AI accuracy.
Responsibilities
Define and execute test plans for both human-written and AI-generated code.
Design regression testing strategies for AI-assisted development workflows.
Collaborate with ML engineers to evaluate model precision, recall, and correctness metrics.
Monitor automated test pipelines integrating AI evaluation steps.
Curate benchmark datasets for fine-tuning (SFT/DPO) based on QA insights.
Define and maintain quality thresholds for PR bot model output.
Promote a data-driven QA culture focused on continuous AI model improvement.
Requirements
3+ years of experience as a QA Engineer testing web or mobile applications.
Solid understanding of software testing principles and automation frameworks (Cypress, Playwright).
Experience working with CI/CD pipelines and test integration tools.
Ability to analyze metrics and interpret performance trends for AI outputs.Hands-on experience with API testing tools (Postman, Charles Proxy).
Interest in LLM evaluation and model monitoring workflows.
Nice to Have
Knowledge of LLMOps tools (Weights & Biases, LangSmith, PromptLayer).
Experience defining custom evaluation metrics for AI-generated outputs.
Basic scripting skills (Python, JavaScript) for building custom QA tools.
Familiarity with prompt engineering and AI-assisted test generation.
Our Mission
Our mission is to digitalize some of the biggest corporations in the world and now, to transform how software itself is built through AI.
Our Values
We work like a family:
Yeah, were coworkers but it feels more like a family of brothers and sisters. Weve got each others backs through challenges, and we dont miss a chance to celebrate the wins (big or small).
We are backed by the biggest companies in the world, but we operate like a startup. We can always count on our colleagues to help us and to challenge us, just like your brother would do.
We show our passion:
Passion isnt just a buzzword for us its the fuel that drives everything we do. It means bringing energy to the team, bringing ideas to the table with fire in your belly (and a smile on your face). We laugh a lot, care even more, and genuinely love what we build. Passion is our heartbeat and it shows in our product.
We live to innovate:
Were not just building tech were change agents. Transformation is in our DNA, and questioning the status quo is what gets us out of bed in the morning. We believe bold ideas move us forward, and for us theres no such thing as a bad idea. Everyones voice matters, and weve created a safe space to dream big, speak up, and shape whats next. We think BIG.
We always deliver:
We make it happen and good is just the starting point we push to make it better tomorrow, and we dont stop until its genuinely awesome. Were a high-performing team that holds itself to higher standards, always going the extra mile to deliver impact, not just output, and were like the postman rain or shine, we always deliver.We say what we think:
We communicate openly with clarity, honesty, and respect. We trust each others intentions and believe that transparency builds stronger, faster teams. Speaking up isnt just welcome, its expected. We dont take things personally we take them forward.
Perks of joining our team
Great team
Competitive Salary
Restaurant Ticket for 170/month
Private Health insurance
Hybrid remote-office workplace
Flexible schedule
Possible intensive timetable in the summer months
24 Holiday days per year
1.000 Referral reward
Filtered water, biscuits, fresh fruit, wide selection of teas and Nespresso
Work in one of the top digital hubs in Barcelona