Your personal AI career agent
AI Quality Assurance Engineer(m/w/x)
Validating AI Hub capabilities and supporting decentralized AI use cases. Understanding of prompt engineering and agentic AI testing required. Flexible hybrid work, relocation support.
Requirements
- Understanding of prompt/context/harness engineering, intent-based testing, spec-driven development, BDD, codified acceptance criteria, feature flagging, A/B testing
- Min. 3 years experience as engineer, strong advocacy/knowledge of SQA, System Testing in Agentic AI
- Min. 2 years experience, familiarity with evaluation frameworks, behavioural/performance testing, observability platforms (e.g., LangSmith, DeepEval, Ragas, Langfuse, Braintrust, Datadog)
- Experience defining test strategies, test plans, acceptance criteria, validation approaches
- Deep understanding of Generative AI systems (e.g. LLM based applications), agentic AI workflows
- Familiarity with evaluation of GenAI outputs (e.g. hallucination risk, consistency, explainability, robustness)
- Understanding of prompt-based system behaviour, orchestration patterns, AI agents
- Familiarity with data pipelines, APIs, system integration patterns
- Ability to translate functional AI requirements to technically testable specifications
- Experience in Agile delivery environments, cross-functional teams
- Strong analytical and problem-solving skills
- Experience in regulated financial services environments is beneficial
Tasks
- Evaluate and validate AI Hub capabilities
- Support decentralized AI use cases
- Define evaluation approaches for AI systems
- Translate AI requirements into testable criteria
- Derive reusable validation methods and best practices
- Promote AI quality assurance methods
- Ensure scalable and compliant AI deployment
- Assess AI system reliability, performance, explainability, robustness
- Implement CI/CD regression gates
- Maintain a golden eval set
- Run evals in CI
- Block rollout on regressions
- Apply best practices in prompt, context, and harness engineering
- Mitigate risks like context rot
- Use spec-driven development frameworks
- Codify clear quality instructions
- Apply feature flagging and A/B testing
- Support continuous improvement of AI solutions
Work Experience
- 3 years
Education
- Vocational certificationOR
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- LangSmith
- DeepEval
- Ragas
- Langfuse
- Braintrust
- Datadog
- APIs
Benefits
Flexible Working
- Flexible work arrangements
- Hybrid model
- Flexible working hours
Retirement Plans
- Company pension/savings plans
Other Benefits
- Relocation support
Childcare
- Childcare facilities
Competitive Pay
- Company share purchasing plan
Mental Health Support
- Mental health and wellbeing programs
Company Bike
- Jobrad bike leasing
Public Transport Subsidies
- Subvention Jobticket
Career Advancement
- Career opportunities within Allianz Group
Learning & Development
- Self-guided learning & development
Social Impact
- Volunteering time
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
Not a perfect match?
- Allianz Global InvestorsFull-timeWith HomeofficeExperiencedFrankfurt am Main
- Allianz Global Investors
Data Engineer(m/w/x)
Full-timeWith HomeofficeExperiencedFrankfurt am Main, München - paiqo GmbH
AI Engineer II - Agentic AI Platform(m/w/x)
Full-timeWith HomeofficeExperiencedPaderborn, Frankfurt am Main - Deloitte GmbH Wirtschaftsprüfungsgesellschaft
Senior Quality Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin, Düsseldorf, Frankfurt am Main, Hamburg, Hannover, Köln, München, Nürnberg, Stuttgart - compeople AG
Quality Assurance Engineering / Testing Professional(m/w/x)
Full-timeWith HomeofficeExperiencedFrankfurt am Main
AI Quality Assurance Engineer(m/w/x)
Validating AI Hub capabilities and supporting decentralized AI use cases. Understanding of prompt engineering and agentic AI testing required. Flexible hybrid work, relocation support.
Requirements
- Understanding of prompt/context/harness engineering, intent-based testing, spec-driven development, BDD, codified acceptance criteria, feature flagging, A/B testing
- Min. 3 years experience as engineer, strong advocacy/knowledge of SQA, System Testing in Agentic AI
- Min. 2 years experience, familiarity with evaluation frameworks, behavioural/performance testing, observability platforms (e.g., LangSmith, DeepEval, Ragas, Langfuse, Braintrust, Datadog)
- Experience defining test strategies, test plans, acceptance criteria, validation approaches
- Deep understanding of Generative AI systems (e.g. LLM based applications), agentic AI workflows
- Familiarity with evaluation of GenAI outputs (e.g. hallucination risk, consistency, explainability, robustness)
- Understanding of prompt-based system behaviour, orchestration patterns, AI agents
- Familiarity with data pipelines, APIs, system integration patterns
- Ability to translate functional AI requirements to technically testable specifications
- Experience in Agile delivery environments, cross-functional teams
- Strong analytical and problem-solving skills
- Experience in regulated financial services environments is beneficial
Tasks
- Evaluate and validate AI Hub capabilities
- Support decentralized AI use cases
- Define evaluation approaches for AI systems
- Translate AI requirements into testable criteria
- Derive reusable validation methods and best practices
- Promote AI quality assurance methods
- Ensure scalable and compliant AI deployment
- Assess AI system reliability, performance, explainability, robustness
- Implement CI/CD regression gates
- Maintain a golden eval set
- Run evals in CI
- Block rollout on regressions
- Apply best practices in prompt, context, and harness engineering
- Mitigate risks like context rot
- Use spec-driven development frameworks
- Codify clear quality instructions
- Apply feature flagging and A/B testing
- Support continuous improvement of AI solutions
Work Experience
- 3 years
Education
- Vocational certificationOR
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- LangSmith
- DeepEval
- Ragas
- Langfuse
- Braintrust
- Datadog
- APIs
Benefits
Flexible Working
- Flexible work arrangements
- Hybrid model
- Flexible working hours
Retirement Plans
- Company pension/savings plans
Other Benefits
- Relocation support
Childcare
- Childcare facilities
Competitive Pay
- Company share purchasing plan
Mental Health Support
- Mental health and wellbeing programs
Company Bike
- Jobrad bike leasing
Public Transport Subsidies
- Subvention Jobticket
Career Advancement
- Career opportunities within Allianz Group
Learning & Development
- Self-guided learning & development
Social Impact
- Volunteering time
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
About the Company
Allianz Global Investors
Industry
FinancialServices
Description
Allianz Global Investors is a leading global active asset manager focused on long-term value creation and sustainability.
Not a perfect match?
- Allianz Global Investors
DevSecOps AI Engineer(m/w/x)
Full-timeWith HomeofficeExperiencedFrankfurt am Main - Allianz Global Investors
Data Engineer(m/w/x)
Full-timeWith HomeofficeExperiencedFrankfurt am Main, München - paiqo GmbH
AI Engineer II - Agentic AI Platform(m/w/x)
Full-timeWith HomeofficeExperiencedPaderborn, Frankfurt am Main - Deloitte GmbH Wirtschaftsprüfungsgesellschaft
Senior Quality Engineer(m/w/x)
Full-timeWith HomeofficeSeniorBerlin, Düsseldorf, Frankfurt am Main, Hamburg, Hannover, Köln, München, Nürnberg, Stuttgart - compeople AG
Quality Assurance Engineering / Testing Professional(m/w/x)
Full-timeWith HomeofficeExperiencedFrankfurt am Main