Senior Automation Test Engineer – AI Systems (f/m/x)

Sii Poland; Bydgoszcz; On-site; PLN 180,000 - 240,000; Full time

Benefits offered by this job

Great Place to Work

Profit sharing

Centre of internal trainings

Medical care

Regular integration events and trips

Job summary

Sii Poland is seeking a Senior QA Engineer to shape the testing strategy for an AI-powered operating system in healthcare marketing. You will own AI/ML evaluation pipelines, drift monitoring, and end-to-end testing across a full-stack architecture including Angular, Node.js, and Python services.

You will design automated test frameworks, implement telemetry, and work with datastores and monitoring tools to ensure high-quality releases.

Qualifications

• 5+ years in software testing, with ≥2 years AI/ML testing or LLM workflows.
• Proficient in Python for testing scripts and JavaScript/TypeScript for Node.js/Angular testing.
• Experience with evaluation frameworks and ML drift monitoring.
• Familiarity with observability tools (Datadog, Grafana).

Responsibilities

• Design, build, and maintain evaluation frameworks for LLMs and agentic harnesses.
• Develop automated scoring, assertions, and test suites for accuracy and reliability.
• Simulate multi-step agent workflows to uncover edge cases.
• Set up monitoring for data drift and model performance in production.
• Implement telemetry and alerting for latency, token usage, and cost.
• Own end-to-end testing across Angular frontend, Node.js backend, and Python AI services.
• Write scalable test scripts in Python and JavaScript/TypeScript.
• Perform API, integration, and performance testing for high-throughput microservices.
• Integrate AI evaluation into CI/CD gates.
• Define and track quality KPIs for software reliability and AI behavior.

Skills

Python

JavaScript/TypeScript

English Advanced

Tools

LangSmith

Langfuse

EvidentlyAI

Ragas

MLflow

Datadog

Grafana

Job description

We are looking for a Senior QA Engineer to join our team and contribute to building an AI-powered operating system for healthcare marketing. In this role, you will go beyond traditional end-to-end testing, owning quality, evaluation, and monitoring for complex AI systems. You will work on real-world production-grade products that create monetizable value, ensuring the stability of our full-stack architecture while designing and scaling AI evaluation pipelines and ML drift monitoring systems. If you are passionate about developing robust test and evaluation frameworks for modern systems powered by AI and ML, we want to hear from you.

Your tasks

• Designing, building, and maintaining evaluation frameworks for Large Language Models (LLMs) and custom agentic harnesses
• Developing automated scoring mechanisms, assertions, and test suites to measure agent accuracy, reasoning reliability, hallucination rates, and tool-use correctness
• Simulating complex, multi-step agent workflows to uncover edge cases in autonomous decision-making
• Collaborating with engineering teams to set up robust monitoring frameworks for data drift, concept drift, and model performance degradation in production
• Implementing telemetry and alerting systems to track latency, token usage, cost efficiency, and output quality over time
• Owning the end-to-end testing strategy across our entire stack, ensuring seamless integration between the Angular frontend, Node.js backend services, and Python-based AI microservices
• Writing clean, maintainable, and scalable automated test scripts in Python and JavaScript/TypeScript
• Performing rigorous API testing, integration testing, and performance/load testing for high-throughput microservices
• Integrating AI evaluation and testing harnesses into our CI/CD pipelines to ensure continuous quality gate enforcement before deployment
• Defining and tracking key quality metrics (KPIs) for software reliability and AI model behavior

Requirements

• Minimum 5 years of experience in software testing or quality engineering, with at least 2 years focused on testing or evaluating AI/ML applications, LLM workflows, or agentic systems
• Proficiency in Python for backend/AI testing scripts and familiarity with JavaScript/TypeScript for Node.js and Angular testing ecosystems
• Experience with evaluation frameworks such as LangSmith, Langfuse, EvidentlyAI, Ragas, or MLflow, and the ability to select appropriate metrics for classification or generation-quality problems
• Familiarity with ML drift monitoring concepts, metrics tracking, and observability tools like Datadog or Grafana
• Strong system-level design skills and the ability to build production-grade test and evaluation infrastructure from the ground up
• Advanced level of English

Nice to have

• Understanding of agentic design patterns and their decomposition into testable units
• Experience working under the regulatory conditions of healthcare systems

Benefits For You

• Great Place to Work
• Solid financial situation
• Contracts with the biggest brands
• Centre of internal trainings
• Many experts you can learn from
• Open and accessible management team
• Profit sharing
• Passion Sponsorship program
• Regular integration events and trips
• Comfortable and well-equipped offices
• MySii app
• Medical care

Job no. JOB-GTXQF

Sii ensures that all hiring decisions are made solely on the basis of qualifications and competence. We are committed to equal and fair treatment of all, regardless of legally protected characteristics. At Sii, we promote a diverse and inclusive work environment, in full compliance with applicable anti-discrimination laws.