ML-QA Engineer

We are looking for a ML-QA Engineer with strong automation experience testing intelligent/agentic applications to join our growing engineering team. You will play a critical role in ensuring the quality and reliability of our platform by developing automated test frameworks, writing robust test cases, and collaborating closely with developers, product owners, and DevOps.

The role goes beyond traditional QA: You will be working with AI-driven, agentic applications that can plan, act, and adapt. Your job will be to make sure they behave correctly, safely, and predictably under real-world conditions.

Key Responsibilities

Design, develop, and maintain automated test frameworks and test scripts using Python

Integrate automated tests into CI/CD pipelines to ensure continuous quality and fast feedback

Collaborate with developers and product managers to identify, reproduce, and resolve defects early in the lifecycle

Define and document test plans, strategies, and acceptance criteria for both deterministic and agentic features

Verify observability and explainability of agent behavior (logs, traces, intermediate actions) to ensure compliance, transparency, and auditability

Perform scenario-based, exploratory, and chaos testing to validate agent decision-making under uncertainty, failure, and edge conditions

Test human-in-the-loop workflows, ensuring proper escalation, overrides, and user safety

Conduct root cause analysis of production issues, including agent misbehavior, and contribute to long-term fixes

Contribute to the development and enforcement of QA standards and best practices

Must-Have Qualifications

3+ years of experience in QA Engineering with a focus on test automation for web and distributed systems

Proficient in Python for developing test scripts, validation tools, and data validation utilities

Hands-on experience with testing frameworks such as PyTest, Selenium, or Playwright for end-to-end and UI testing.

Strong understanding of software testing methodologies, including unit, integration, system, and end-to-end testing.

Familiarity with REST APIs and tools like Postman or Swagger for API testing

Strong problem solving skills with the ability to think beyond "happy path" testing.

Understanding of data validation pipeline and data pipeline testing, ensuring integrity and reproducibility across datasets

Nice-to-Have Qualifications Experience testing agentic or AI-driven applications (e.g., autonomous decision-making, multi-step workflows)*

Experience with scenario-based or chaos testing frameworks

Familiarity with observability and monitoring tools (e.g., Datadog, Grafana, AWS CloudWatch) to validate agent behavior

Experience testing microservices or serverless architectures on AWS

Familiarity with CI/CD tools like GitHub Actions, Jenkins, or GitLab CI.

Knowledge of security and guardrail testing (role-based access, safe action validation)

Experience writing performance and load tests for AI interface endpoints using Locust or k6.

Qualities we Value: Systems thinker:* You see how parts connect and anticipate failure points

Exploratory mindset: Comfortable testing for unknown unknowns

Domain curiosity: Willingness to deeply understand how the agent is supposed to act in the real world

Ethical awareness: You care about safety, fairness, and unintended consequences in AI systems

Collaborative: You work closely with engineers, product, and operations to build trust in our platform

At Beroe X nnamu GmbH, we prioritize a balanced work-life experience.

Here’s what we offer you:

4-Day Work Week \& 30 Days Paid Vacation – More time to recharge

Competitive Compensation – Fair salary and comprehensive benefits.

Monthly Benefits Allowance – €40/month in vouchers for fitness and other perks with Probonio

Flexible Work Arrangements – Work the way that suits you. Professional Development – Access to training and certifications.

Team Events – Bi-annual company events and monthly lunch get-togethers.

Work Abroad Flexibility – Remote work from the EU or selected non-EU countries for up to 8 weeks a year with travel insurance coverage

We operate on a hybrid model with offices in Berlin and Munich, offering a 32-hour, 4-day workweek.

This means:

In-Office Collaboration: Work from the office two days a week

Manage Your Own Hours: Flexibility to work around your needs as long as team goals are met.

Our Culture

We are committed to fostering a collaborative, innovative and inclusive work environment where everyone’s ideas matter. We know that diverse teams lead to better outcomes and welcome applicants from all backgrounds.#### About us

At Beroe x nnamu GmbH, we are committed to empowering procurement teams to make informed, strategic decisions that drive real impact. By integrating AI and game theory, our Software as a Service (SaaS) platform, nnamu.negotiations, delivers a groundbreaking approach to complex, yet autonomous negotiations.

nnamu.negotiations delivers additional total-value-of-ownership savings efficiently and effectively for buyers with no prior knowledge of game theory required. By combining our world class proprietary AI with an unmatched, unique database of over EUR 400bn actual game theory project data we help clients uncover incremental value in their negotiations, driving outcomes that were previously out of reach.

Beroe x nnamu GmbH is now a Beroe, Inc. group entity. Beroe is a global leader in procurement intelligence. Beroe has been on procurement’s leading edge since the company’s founding in 2006, bringing a world of insights forward. The unique combination of Beroe’s expertise, AI tools, and vast amounts of reliable data enable organizations to make smarter, faster, better procurement decisions. Not tomorrow, not today, but now. Selected by ProcureTech as one of the “most pioneering Analytics, Data and Intelligence solutions in 2024”, Beroe helps thousands of organizations sift through the data noise, mitigate risk, face fewer surprises, and ultimately gain a competitive edge.

With nnamu’s cutting-edge AI and Beroe’s trusted market intelligence, we are unlocking game-changing possibilities for procurement teams worldwide

The Challenge We are Solving

Despite the proven potential of game theory to enhance negotiation outcomes significantly – potentially unlocking an incremental USD 1 Trillion of value – its application in business negotiations remains rare, inconsistent, and hard to scale. This gap presents a vast opportunity but also a challenge that many companies have yet to overcome. Beroe x nnamu GmbH is pioneering the use of AI-powered game theory to make complex negotiation strategies accessible, scalable, and incredibly effective for organizations worldwide.