Senior AI Platform Engineer — Agentic Systems & Observability

Cloudbeds; Newark (NJ); On-site; USD 140,000 - 210,000; 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 a senior engineer to design, build, and operate customer-facing AI platform services and features, including agent runtimes, workflow orchestration, and tool integrations. You will own model evaluation, tracing, and observability, while leading technically and collaborating with product, design, data, security, and engineering teams.

The role requires 5+ years building production systems, strong Python, and experience with agentic systems or LLM-powered workflows, plus

Qualifications

• 5+ years of experience building and operating production systems.
• Strong production Python skills.
• Experience with agentic systems or LLM-powered workflows.
• Experience with distributed systems, APIs, testing, cloud infrastructure, and AI evaluation or observability.
• Ability to work across PHP and Java services and communicate in business-level English.

Responsibilities

• Design, build, and operate customer-facing AI platform services and product features, including agent runtimes, workflow orchestration, tool execution, and integrations with existing services.
• Own model evaluation, tracing, observability, and quality feedback loops while providing technical leadership and collaborating across product, design, data, security, and engineering.

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

LangChain

LangSmith

LangGraph

MCP

Retrieval-Augmented Generation

Vector Databases

AWS

Docker

PostgreSQL

PHP

Java

Python

Job description

Cloudbeds is seeking a senior engineer to design, build, and operate customer-facing AI platform services and features, including agent runtimes, workflow orchestration, and tool integrations. You will own model evaluation, tracing, and observability, while leading technically and collaborating with product, design, data, security, and engineering teams.

The role requires 5+ years building production systems, strong Python, and experience with agentic systems or LLM-powered workflows, plus