AI Reliability Engineer - On-Site | Plano (Contract)

Ziosk; Dallas (TX); On-site; USD 120,000 - 150,000; Part time

Job summary

Ziosk is seeking a highly experienced AI Software Engineer-Reliability on a contract, on-site basis in Plano, TX to strengthen production resilience. You will apply AI-driven tooling, AI-assisted debugging, and robust log analysis to accelerate root-cause diagnoses.

You’ll work across Android (C++, Kotlin, React Native) and .NET stacks, build automated diagnosis pipelines, and integrate changes into CI/CD while reducing MTTR and recurring incidents.

Qualifications

• 3+ years of professional software engineering experience, including production environments.

Responsibilities

• Diagnose and resolve production issues across Android (C++, Kotlin, React Native) and .NET systems using logs, telemetry, and AI-assisted analysis.
• Design and improve AI-enabled log analysis and incident triage workflows to accelerate root cause identification.
• Leverage AI-assisted development tools to generate, test, and validate code fixes efficiently.
• Identify repetitive break/fix patterns and develop AI-driven automation to reduce manual debugging effort.
• Integrate AI-supported diagnostics and automation into CI/CD pipelines and defect tracking systems.
• Implement durable fixes that reduce repeat incidents and improve overall system reliability.
• Build and refine retrieval-based (RAG) workflows to surface historical incident context and detect recurring patterns.
• Document resolutions and automation improvements to expand AI-assisted resolution coverage and reduce MTTR.

Skills

C++

C#

Kotlin

Android

Debugging

AI tooling

CI/CD

REST APIs

Multithreading

Collaboration

Tools

Copilot

LLM workflows

Job description

Ziosk is seeking a highly experienced AI Software Engineer-Reliability on a contract, on-site basis in Plano, TX to strengthen production resilience. You will apply AI-driven tooling, AI-assisted debugging, and robust log analysis to accelerate root-cause diagnoses.

You’ll work across Android (C++, Kotlin, React Native) and .NET stacks, build automated diagnosis pipelines, and integrate changes into CI/CD while reducing MTTR and recurring incidents.