Senior/Mid-level Quality Engineering Analyst

Jobgether SRL; Brasil; On-site; BRL 120,000 - 170,000; Full time

Benefits offered by this job

Remote work Brazil

AI-focused environment

Technical scope exposure

Cross-functional collaboration

Professional growth

Impactful work

Job summary

Lever, Inc. is seeking a Senior/Mid-level Quality Engineering Analyst based in Brazil. You will ensure quality, reliability, and safety of AI-powered conversational experiences, testing LLMs, flows, APIs, and integrations. You will use automation, cloud environments, and databases to improve testing efficiency and outcomes.

You will collaborate with engineers, designers, and stakeholders in an evolving quality engineering environment that combines AI and software testing with business context.

Qualifications

• Hands-on QA across complex software flows.
• Experience with test automation frameworks and CI.
• Ability to translate AI/LLM behavior into tests.

Responsibilities

• AI & LLM Testing: design tests for accuracy, safety, relevance.
• Functional & Automated Testing: run tests across flows and APIs.
• Generative AI Validation: reduce hallucinations and misalignment.
• Integration Quality: document issues and drive fixes with eng.
• API Testing: validate RESTful APIs and data flows.
• User Experience Validation: assess UX and performance of AI journeys.
• Cross-functional Collaboration: communicate with engineers and designers in agile teams.

Skills

QA Experience

Test Automation

AI/LLM Knowledge

API Testing

Generative AI Tools

Cloud & DBs

Agile Collaboration

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior/Mid-level Quality Engineering Analyst based in Brazil.

As a Senior/Mid-level Quality Engineering Analyst, you will play a key role in ensuring the quality, reliability, and safety of AI-powered conversational experiences.
You will work on complex testing scenarios involving LLMs, conversational flows, APIs, and enterprise integrations.
The role combines traditional software quality practices with innovative approaches to validating non-deterministic AI behavior.
You will help identify inaccuracies, hallucinations, integration issues, and usability challenges before they impact end users.
Working closely with engineers, designers, and other stakeholders, you will contribute to stable and high-quality customer deliveries.
You will also leverage automation, cloud environments, databases, and generative AI tools to make testing and diagnostics more efficient.
This is an opportunity to contribute to an evolving quality engineering environment where AI, software testing, and business context come together.

Accountabilities

• AI & LLM Testing: Analyze LLM behavior and design rigorous test scenarios that assess the accuracy, consistency, safety, and contextual relevance of AI-generated responses.
• Functional & Automated Testing: Execute functional, exploratory, regression, and automated tests across conversational flows and APIs to ensure reliable and stable deliveries.
• Generative AI Validation: Establish validation routines for generative models, identifying and mitigating hallucinations while ensuring AI interactions remain aligned with business contexts.
• Integration Quality: Investigate integration anomalies, document issues with detailed findings, and collaborate with engineering teams to accelerate resolution and continuous improvement.
• API Testing: Validate RESTful APIs, integrations, and data flows using appropriate testing tools and techniques.
• User Experience Validation: Assess the usability, responsiveness, and overall performance of AI-powered journeys to help deliver seamless user experiences.
• Cross-functional Collaboration: Work within agile environments and maintain strong technical communication and alignment with engineers, designers, and multiple stakeholders.

Requirements

• Quality Engineering Experience: Hands-on experience creating and executing functional, exploratory, and regression tests for complex software flows.
• Test Automation: Practical experience with test automation frameworks such as Cypress or Robot Framework, ideally within continuous testing environments.
• AI & LLM Understanding: Ability to translate expected AI and LLM behavior into structured test scenarios that assess safe, accurate, and contextually appropriate interactions.
• API Testing: Experience testing RESTful APIs with tools such as Postman and validating integrations and data traffic.
• Generative AI Tools: Comfortable using generative AI and modern productivity tools such as GitHub Copilot to accelerate script development, testing, and troubleshooting.
• Technical Environment: Practical experience working with cloud environments and querying both relational and non-relational databases.
• Agile Collaboration: Experience working in agile teams, with the ability to communicate effectively and maintain technical alignment across multiple stakeholders.

Benefits

• Remote Work: Fully remote position based in Brazil, offering the flexibility to work from anywhere within the country.
• AI-Focused Environment: Opportunity to work directly with LLM-powered conversational experiences and emerging generative AI technologies.
• Technical Scope: Exposure to software quality engineering, test automation, APIs, cloud environments, databases, and complex integrations.
• Cross-functional Collaboration: Work closely with engineering, design, and other stakeholders on enterprise-level technology initiatives.
• Professional Growth: Opportunity to deepen expertise in AI validation, automation, quality engineering, and modern software development practices.
• Impactful Work: Contribute to the reliability, safety, and effectiveness of AI-driven experiences used in complex customer environments.