AI Application Developer Posted Trending

The FortiOS Release QA team is a group of over 90 staff dedicated to ensuring Fortinet products meet elite market standards before release. We are seeking an AI Application Developer to architect an end-to-end, closed-loop release cycle. You will design an AI-governed control plane that autonomously manages the software lifecycle: reasoning over feature specifications to create test plans, executing and verifying tests, managing the bug lifecycle, and ultimately generating customer-facing documentation and videos once a feature is verified.

Your goal is to minimize manual toil while ensuring elite quality and providing immediate value to the end-user upon release.

• Autonomous Spec-to-Plan Reasoning:
  Design systems using LLMs to ingest feature specifications and technical documentation to autonomously generate comprehensive test plans and high-coverage test scripts
• AI-Powered Test Case Generation:
  Utilize AI to author test cases derived from design requirements rather than existing code, ensuring that tests verify the intended functionality and avoid implementation-based confirmation bias.
• AIOps for Root Cause Analysis:
  Develop and deploy AIOps solutions to process massive log records and metrics from automation jobs, identifying the "few that matter" to automate root cause analysis and reduce manual triage toil.
• Intelligent Execution & Prioritization:
  Implement machine learning models for test case prioritization to maximize fault detection and optimize execution throughput within the CI/CD pipeline.
• Autonomous Bug Lifecycle Management:
  Build agents for automatic bug filing, tracking, and verification, including performing autonomous re-testing to verify fixes before they reach human review.
• Post-Verification Content Generation:
  Develop AI systems to autonomously generate technical documentation and instructional video content for customers following successful feature verification. Use LLMs to synthesize technical specs and verification results into structured, human-readable explanations and multimedia artifacts to accelerate customer onboarding.
• Governance & Human-in-the-Loop:
  Embed risk-weighted decision models to ensure that final release acknowledgements are backed by auditable AI-driven insights while preserving human oversight for high-impact decisions

• Education:
  
  Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or a related technical field.
• AI/ML
  
  Experience:
  
  2–3 years of experience building machine learning, natural language processing (NLP), or generative AI-driven applications.
• Programming Proficiency:
  Strong proficiency in Python and familiarity with common machine learning libraries such as Num Py, Pandas, Scikit-learn, Tensor Flow, or PyTorch.
• LLM Application Development:
  Proven experience building applications with Large Language Models (LLMs) using strategies like prompt engineering and Retrieval-Augmented Generation (RAG).
• Dev Ops Knowledge:
  Hands-on experience with CI/CD tools, containerization (Docker, Kubernetes), and the integration of AI into automated testing tool chains.
• Analytical Problem Solving:
  Ability to reason over complex "brownfield" tasks where AI must interact with large, existing codebases and distributed systems.
• Communication:
  Effective communication skills to explain AI-driven insights, behaviors, and constraints to both technical QA staff and non-technical stakeholders.

• Knowledge of Specification-Driven Testing paradigms and formal verification.
• Experience with Self-Correction and Reinforcement Learning from execution feedback to improve agent proficiency over time.
• Understanding of Zero Trust Architecture (ZTA)…