Senior AI Platform Engineer - LLM Workflows & Observability

Cloudbeds; Detroit (MI); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Paid Time Off

Fully Paid Parental Leave

Home Office Stipend

Professional Development Courses

Manager Training

Upskilling

Knowledge Transfer

Job summary

Cloudbeds is seeking an experienced engineer to design, build, and operate customer-facing AI platform services. You will oversee agent runtimes, workflow orchestration, tool execution, and evaluation capabilities, collaborating with product and engineering teams to deliver reliable AI features in production.

You will work on distributed systems, APIs, and cloud infrastructure, ensuring observability and quality while integrating with PHP and Java services. Strong Python skills are essential.

Qualifications

• Requires at least five years of experience building and operating production software systems.
• Strong production Python skills and hands-on experience with agentic systems or LLM-powered workflows.
• Experience with distributed systems, APIs, cloud infrastructure, testing, and AI evaluation or observability.
• Comfortable integrating with PHP and Java services.

Responsibilities

• Design, build, and operate customer-facing AI platform services and product features, including agent runtimes and workflow orchestration.
• Lead reliability through evaluation and observability, collaborating with product and engineering teams.
• Integrate AI systems into production environments with scalable, maintainable architecture.
• Provide technical leadership and mentoring across teams to improve system quality.

Skills

Python

Agentic Systems

LLM Workflows

LangChain

LangSmith

LangGraph

MCP

Retrieval-Augmented Generation

Vector Databases

AI Evaluation

LLM Observability

PHP

Java

PostgreSQL

AWS

Docker

Tools

PostgreSQL

AWS

Docker

APIs

Job description

Cloudbeds is seeking an experienced engineer to design, build, and operate customer-facing AI platform services. You will oversee agent runtimes, workflow orchestration, tool execution, and evaluation capabilities, collaborating with product and engineering teams to deliver reliable AI features in production.

You will work on distributed systems, APIs, and cloud infrastructure, ensuring observability and quality while integrating with PHP and Java services. Strong Python skills are essential.