Why is Perficient the best option?

Perficient is a leading global digital consultancy and has a presence around the globe transforming and connecting the most prominent brands with their customers. At Perficient, we seek to grow alongside professionals promoting agile cultures and values as we challenge, champion, and celebrate our people for us to build a great future together.

Job Summary

At Perficient QA - LLM Engineer is a technical role that demands creativity and innovation to design effective strategies for testing software products. This position involves developing, executing, and debugging automated test scripts, with a strong focus on prompt engineering, output quality evaluation, and AI-driven implementations. The ideal candidate excels at leading cross-functional teams and translating Large Language Model (LLM) concepts into practical, business-aligned strategies.

What do you need to come aboard?

• Bachelor's degree in Computer Science, Computer Engineering, or Information Technology related disciplines.
• Strong problem-solving skills and ability to debug complex model behaviors.
• High English skills on written and verbal communication to build a trusting relationship with major project stakeholders.
• Demonstrate good attitude, ability to analyze requirements and must be detail oriented.
• Ability to identify risks, errors, or failures in software applications.
• Proven experience in QA and Testing projects within agile development environments.
• Strong background in Functional, Regression, Integration, and System Testing.
• Proficiency in Python and APIs to develop and integrate open-source libraries into unit and integration tests.
• Hands-on experience with test automation projects using tools such as Postman, Selenium, Cypress, JavaScript, TypeScript, Playwright, JMeter, etc.
• Solid understanding of Natural Language Processing (NLP) and Large Language Models (LLMs), including architecture knowledge (e.g., GPT) and experience with related toolsets (e.g., OpenAI API).
• Expertise in using data manipulation libraries to integrate data preprocessing and ingestion workflows into LLM evaluation pipelines.
• Experience in prompt engineering with focus on evaluating output quality, prompt response structure, metadata, and consistency across diverse use cases.
• Proven track record of testing and evaluating chatbots and conversational AI products.
• Familiarity with ethical AI principles, bias mitigation, and responsible model evaluation.
• Excellent communication skills with the ability to work across cross-functional teams and sharing insights and strategies related to LLMs.

What can we offer you?

• Law benefits
• Certifications
• Internal & External Courses
• English Classes
• Medical Insurance (Personal and Familiar)
• Life Insurance
• Savings Fund
• Pantry Vouchers
• Additional Holidays

*Once you apply you accept the terms and conditions of Perficient in Latin America and agree to be contacted by the Talent Acquisition team.