AI/ML Engineer

About the role

PagerDuty is seeking an early‑career AI/ML Engineer to help build and ship AI systems that run at massive scale on its Operations Cloud platform. You will work on incident‑management AI agents, event intelligence, and LLM‑powered capabilities, moving prototypes into reliable production services.

Key responsibilities

• Develop AI‑powered features such as LLM agents, retrieval pipelines, and event‑intelligence components that process high‑volume, real‑time data.
• Build and maintain supporting infrastructure, including prompt orchestration, tool/API integrations, and inference services, with a focus on testing and observability.
• Analyze latency, throughput, cost, and reliability of LLM‑based services and apply optimizations in code.
• Advance prototypes toward production, implementing evaluation and monitoring loops to ensure accuracy and trustworthiness.
• Collaborate with platform, product, and applied‑research teams to translate requirements into working code.
• Grow through code reviews, pairing, and mentorship, gradually taking on greater ownership.

Required profile

• 2+ years of software engineering experience delivering production software.
• Degree in Computer Science or a related field, or equivalent practical experience.
• Strong programming fundamentals and ability to work across application and model code.
• Hands‑on experience building real‑world solutions with large language models, prompting, retrieval, or agent frameworks.
• Exposure to distributed systems concepts.

Required skills

• AI/ML
• Large language models (LLMs)
• Prompt engineering
• Information retrieval
• Agent frameworks
• Distributed systems