Reach out directly about this role
Remote · outside RF and RB · conversational English__**
We are Aspirity Solution, a development studio with over 10 years of experience in creating web and mobile applications, no-code solutions, and intelligent AI agents for clients worldwide.
We are currently looking for a QA Engineer who will be responsible for the quality, stability, and predictability of AI agents and LLM systems.
Responsibilities:
Testing and evaluating the performance of AI agents (dialogue and cognitive systems).
Developing and conducting eval tests to verify the correctness, robustness, and stability of agent behavior.
Preparing test cases and scenarios for functional and non-functional testing.
Analyzing agent behavior with non-standard input data, identifying logical errors and problems in prompts.
Closely interacting with developers and prompt engineers to improve models and test pipelines.
Supporting and developing test automation and QA processes within the AI team.
Maintaining technical documentation and describing best practices.
Requirements
QA experience (manual or automation) of 2+ years.
Practical experience testing AI agents or chatbots.
Understanding of AI agents, LLM systems, and prompt engineering principles.
Experience with eval tools (OpenAI Evals, DeepEval, LangChain Evals, or equivalents).
Experience with automated testing (preferably for AI agents).
Proficient in Python for writing tests and utility scripts.
Skills in working with Git and bug tracking systems.
English language proficiency from B2 for working in an international team.
Residency outside of RF and RB.
Willingness to work in the PT time zone: from 7:00 to 16:00 PT. (America time, Washington)
Will be a plus
Experience with LangChain, vapi, Synthflow, or other AI agent creation tools.
Experience analyzing LLM outputs based on quality metrics: accuracy, coherence, relevance.
Understanding of CI/CD processes and basic monitoring tools.
Participation in building test architecture for AI systems.
We offer
Fully remote work format.
Work in a strong team of developers, ML engineers, and AI specialists.
Opportunity for professional growth in QA for LLM and AI agent systems.
Payment based on qualification — from 20 USD/hour.
from 20 USD
per hour
from 2 years
Experience
Remote
Work Format
Middle
Grade
B2 - Upper-Intermediate
English Level
QA Testing
Specialization
AI
Industry
Outsourcing
Company Type
By job title
QA Testing
Specialization
AI
Industry
Outsourcing
Company Type