AI Reliability Engineer
Role summary
Palona is seeking an AI Reliability Engineer to build and maintain the engineering discipline for their generative AI platform in the hospitality industry. This role focuses on ensuring AI systems perform reliably by designing and implementing observability systems, automated testing for agent output quality, and robust CI/CD pipelines. You will manage production infrastructure, build tooling for AI agent performance, and architect new systems to address reliability and quality challenges. The position requires a minimum of 2 years of software engineering experience, proficiency in Python, cloud platforms (AWS, Azure, or GCP), and monitoring tools. Familiarity with CI/CD, IaC, and distributed systems is also necessary. Preferred qualifications include experience with automated testing, LLM evaluation, and AI agent systems.
Palona brings the newest advancements in generative, multimodal AI, Real World AI, to the hospitality industry. Our engineers deliver at a fast pace to stay ahead of the AI industry, employing generative AI models to power products that are constantly evolving. In this environment, traditional software excellence principles must adapt to probabilistic outputs -- AI systems don't fail the way conventional software does. This role exists to build the engineering discipline that catches failures before customers do.
You will work across evaluation pipelines, observability, cloud infrastructure, and CI/CD for Palona's AI agent platform. The role is equal parts DevOps and AI reliability: managing production infrastructure while building the tooling that keeps AI agents performing at quality.
Responsibilities
As an AI Reliability Engineer, you will:
- Design and build observability systems that detect quality degradation, latency issues, and system anomalies in production, including instrumentation, dashboards, and alerting
- Write and maintain automated tests for agent output quality, including deterministic checks and LLM-as-judge evaluations
- Develop release and validation systems that automate deployments across environments and enforce quality gates for AI-powered products
- Build and evolve platform infrastructure across environments using infrastructure as code, with a focus on reliability, scalability, and cost efficiency
- Build and extend evaluation pipelines that assess AI agent conversation quality, accuracy, and safety, collaborating with product and engineering to evolve evaluation criteria
- Design and build internal tools and services that support AI reliability, evaluation, and operational workflows
- Architect new systems from scratch to address emerging reliability and quality challenges across the AI agent platform
- Write production-grade code for reliability and evaluation infrastructure, contributing as a software engineer — not just an operator
Requirements
Required
- Minimum 2 years of professional software engineering experience
- Proficiency in Python
- Experience with cloud platforms (AWS, Azure, or GCP)
- Experience with monitoring and observability tools (Datadog, CloudWatch, Grafana, or similar)
- Familiarity with CI/CD pipelines and infrastructure as code
- Experience with APIs and distributed systems
- Willingness to learn new AI/LLM concepts, frameworks, and technologies
Preferred
- Experience writing test frameworks or automated evaluation systems
- Experience building internal tools or developer platforms
- Exposure to LLMs, prompt engineering, or AI agent systems
- Startup experience, or ability to thrive in fast-paced environments
- Background in NLP, computer vision, or AI agent systems
Benefits
- Health Care Plan (Medical, Dental & Vision)
- Retirement Plan (401k, IRA)
- Life Insurance (Basic, Voluntary & AD&D)
- Paid Time Off (Vacation, Sick & Public Holidays)
- Family Leave (Maternity, Paternity)
- Short Term & Long Term Disability
- Training & Development
- Work From Home
- Free Food & Snacks
- Stock Option Plan