Senior AI/ML Engineer

The role

You will design and build AI-powered features including LLM agents, retrieval, and event intelligence. You will architect systems for agent and prompt orchestration, retrieval pipelines, and low-latency inference at scale.

What you will do

• Design and build AI-powered features like LLM agents, retrieval, and event intelligence.
• Architect systems for agent and prompt orchestration, retrieval pipelines, and tool/API integrations.
• Manage low-latency inference and evaluation at scale.
• Reason about consistency, throughput, fault tolerance, and cost across services.
• Take AI features from prototype to production.
• Establish evaluation, guardrail, observability, and improvement loops.
• Partner with platform, product, and applied-research teams.
• Raise the bar through reviews and mentorship.
• Help shape the team's technical direction.

Required qualifications

• 5+ years of software engineering experience.
• Experience building and operating production distributed systems.
• Hands-on experience building and shipping AI systems in production.
• Strong programming fundamentals.
• Solid grounding in applied AI fundamentals: prompting, retrieval, agent patterns, and LLM evaluation and guardrails.
• Experience with cloud infrastructure (AWS, GCP, or Azure).
• Experience with containers and orchestration (Kubernetes).
• Strong communication and collaboration skills.

Nice to have

• Experience with LLMOps tooling and patterns.
• Deep experience serving LLM-based systems in production.
• Background in anomaly detection, event correlation, or applied problems in observability, AIOps, or reliability.
• Familiarity with LLM APIs and frameworks such as LangChain or LlamaIndex.
• Familiarity with vector databases.
• Familiarity with distributed data/compute tools such as Kafka, Airflow, or Spark.
• Contributions to open-source AI or distributed-systems projects.

Benefits

• Competitive salary
• Comprehensive benefits package
• Flexible work arrangements
• Company equity
• ESPP (Employee Stock Purchase Program)
• Retirement or pension plan
• Generous paid vacation time
• Paid holidays and sick leave
• Dutonian Wellness Days & HibernationDuty
• Paid parental leave: 22 weeks for pregnant parent, 12 weeks for non-pregnant parent
• Paid volunteer time off: 20 hours per year
• Company-wide hack weeks

Before you apply

• Candidates must reside in an eligible location.
• Cannot employ candidates residing in specific regions of Australia, Canada, and the United States.

About the company

PagerDuty, Inc. is a global leader in AI-first digital operations. The PagerDuty Platform orchestrates AI agents and automated workflows for organizations scaling resilient, autonomous operations.