AI Software Development Engineer in Test (AI)

TL;DR

AI Software Development Engineer in Test (AI/Python): Designing and implementing AI-powered testing frameworks and evaluation pipelines for LLM outputs and RAG architectures with an accent on hallucination detection and agent validation. Focus on automating validation for multi-agent workflows, building synthetic datasets, and upskilling the QA guild in AI-native quality engineering.

Location: Remote (Must be based in Argentina)

Company

hirify.global (Network Solutions) is a digital identity authority providing domain security, brand protection, and infrastructure management for online businesses.

What you will do

• Champion the adoption of AI-powered testing tools and self-healing frameworks across the QA Guild.
• Design evaluation (Evals) frameworks for LLM outputs, covering hallucination, groundedness, toxicity, and safety guardrails.
• Validate RAG architectures, including chunking strategies, embedding quality, and vector search relevance.
• Develop scalable UI and API automation frameworks using Python, Robot Framework, and Playwright/Selenium.
• Test multi-agent orchestration workflows, including agent memory, context retention, and MCP integrations.
• Integrate automation and quality gates into CI/CD pipelines such as GitHub Actions, Jenkins, and Azure DevOps.

Requirements

• Must be based in Argentina.
• Strong programming experience in Python.
• Hands-on experience with AI/LLM testing, prompt engineering, and AI Evals.
• Practical experience with RAG systems, AI agents, and vector databases.
• Experience with CI/CD pipelines, Docker, Kubernetes, and at least one major cloud platform (AWS, Azure, OCI, or GCP).
• Proficiency in SQL and experience with API and UI automation testing.

Nice to have

• Experience with Robot Framework and Playwright.
• Knowledge of LangChain, LangGraph, LlamaIndex, CrewAI, or Semantic Kernel.
• Experience with AI Red Teaming or LLM security testing (prompt injection, jailbreaks).
• Familiarity with MLOps workflows and performance testing.

Culture & Benefits

• Flexible work environment scenarios: work-from-home, hybrid, or office-based.
• Health care (OSDE 310), monthly salary reviews, and annual bonuses.
• Professional development via tuition reimbursement, LinkedIn Learning, and in-company English lessons.
• Additional "F5" extra days off and internet reimbursement.
• Inclusive environment with over 20 affinity groups and opportunities to work on global, multicultural projects.