About the company
PagerDuty is a leader in Digital Operations Management. In an always-on world, organizations of all sizes trust PagerDuty to help them deliver a perfect digital experience to their customers, every time. Teams use PagerDuty to identify issues and opportunities in real time and bring together the right people to fix problems faster and prevent them in the future.
Responsibilities
- Contribute to AI-powered features — LLM agents, retrieval, and event intelligence — that operate on high-volume, real-time data, with support and guidance from senior engineers.
- Help build and maintain the systems behind them — prompt and agent orchestration, retrieval pipelines, tool/API integrations, and inference services — writing code, adding tests, and improving observability.
- Learn to reason about latency, throughput, cost, and reliability of LLM-powered services, and apply those lessons in the code you write.
- Help take AI features from prototype toward production, and support the evaluation and monitoring loops that keep them accurate and trustworthy over time.
- Partner with platform, product, and applied-research teams, asking good questions and turning requirements into working code.
- Grow through code review, pairing, and mentorship, and steadily take on more ownership as you develop.
Requirements
- 2+ years of software engineering experience building and shipping production software.
- Degree in CS/a related field, or equivalent practical experience.
- Solid programming fundamentals and comfort moving between application code and AI/model code.
- Hands-on experience with modern AI — building something real with LLMs, prompting, retrieval, or agent frameworks.
- Some exposure to distributed systems and how software runs reliably at scale, and eagerness to deepen it.
- Strong communication and collaboration skills.
Nice to have
- Personal, academic, or internship projects involving LLM apps, agents, RAG, or backend services.
- Exposure to cloud infrastructure (AWS, GCP, or Azure), containers, or Kubernetes.
- Familiarity with the ecosystem — e.g. LLM APIs and frameworks such as LangChain or LlamaIndex, vector databases, and orchestration/streaming tools like Kafka or Airflow.
- Interest in agentic systems, evaluation and guardrails for LLMs, or applied problems like anomaly detection and event correlation.
- Contributions to open-source projects.
Conditions
- PagerDuty operates a hybrid work model with offices in 8 major cities: Atlanta, Lisbon, London, San Francisco, Santiago, Sydney, Tokyo, and Toronto.
- Candidates must reside in an eligible location, which vary by role.