AI Software Engineer-Reliability
Job Description
Ziosk is seeking an experienced AI Software Engineer-Reliability (Contract) to strengthen production resilience in Plano, TX.
Responsibilities
- Diagnose and resolve complex production incidents across Android (C++, Kotlin, React Native) and .NET systems using logs, telemetry, and AI-assisted analysis
- Develop and improve AI-enabled log analysis and incident triage workflows to speed up root cause identification
- Use AI-assisted development tools to generate, test, and validate code fixes efficiently
- Detect recurring break/fix patterns and build AI-driven automation to reduce manual debugging effort
- Embed AI-supported diagnostics and automation into CI/CD pipelines and defect tracking processes
- Deliver durable fixes aimed at reducing repeat incidents and improving platform reliability
- Build and refine retrieval-based (RAG) workflows to surface historical incident context and identify recurring patterns
- Document incident resolutions and automation improvements to expand AI-assisted resolution coverage and lower MTTR
Requirements
- 3+ years of professional software engineering experience, including production environment work
- Proficiency in C++, C#, Kotlin, and Android development
- Strong debugging and root cause analysis skills across multiple platforms
- Hands-on use of AI-assisted development tools (example: Copilot, LLM-based workflows) as part of daily engineering
- Practical experience building or contributing to AI-driven automation workflows (log analysis, retrieval-based systems, task automation)
- Understanding of RESTful APIs, multithreading, memory management, and performance troubleshooting
- Experience with version control and CI/CD pipelines to deploy and validate fixes safely
- Ability to analyze recurring defects and propose automation or systemic improvements
- Strong communication skills and ability to collaborate with engineering and operations teams
Technologies
- C++, C#, Kotlin, Android, React Native, .NET
- RESTful APIs, CI/CD
- Copilot
- LLM-based workflows
- Retrieval-based (RAG) workflows
NICE TO HAVE
- Experience with Point of Sale (POS) solutions, especially in hospitality environments
- Familiarity with EMV Payments and payment processing systems
- Exposure to Digital Content Management platforms and workflows
- Experience with embedded systems or hardware integration
- Knowledge of cloud platforms (example: Azure, AWS) and backend services
- Familiarity with Agile methodologies and ticketing systems (example: Jira)
Location: Plano, TX (onsite) | Experience: 3+ years | Job type: Contract