P

PagerDuty

Real-time incident management and on-call platform

Senior AI/ML Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeLisbon, Portugal

About the Job

Requirements

  • At least 5 years of software engineering experience, including meaningful experience building and operating production distributed systems such as high-throughput services, streaming or event-driven architectures, or large-scale data platforms.
  • Hands-on experience building and shipping production AI systems, including LLM-powered applications, agents, or retrieval and associated orchestration, serving, and evaluation.
  • Strong programming fundamentals and comfort working across systems and AI/application code.
  • Solid grounding in applied AI fundamentals, including prompting, retrieval, agent patterns, and evaluating and guardrailing LLM behavior.
  • Experience with cloud infrastructure such as AWS, GCP, or Azure, containers, and orchestration with Kubernetes.
  • A pragmatic, reliability-minded approach to building systems that work correctly at scale and articulating trade-offs.
  • Strong communication and collaboration skills, and a track record of improving the quality of teams and systems.

Responsibilities

  • Design and build AI-powered features, including LLM agents, retrieval, and event intelligence, that operate on high-volume, real-time event streams from problem framing through production deployment and monitoring.
  • Architect and own the systems behind AI features, including agent and prompt orchestration, retrieval pipelines, tool and API integrations, and low-latency inference and evaluation at scale.
  • Reason about consistency, throughput, fault tolerance, and cost across services that must remain reliable under bursty, unpredictable load.
  • Take AI features from prototype to production and establish evaluation, guardrail, observability, and improvement loops to maintain accuracy and trustworthiness.
  • Partner with platform, product, and applied-research teams to define success and integrate AI into existing services.
  • Raise the technical bar through example, reviews, and mentorship, and help shape the team’s technical direction.

Desired Qualifications

  • Experience with LLMOps tooling and patterns, including evaluation harnesses, prompt and version management, tracing and observability for agents, and online/offline evaluation consistency.
  • Deep experience serving LLM-based systems in production, including retrieval-augmented generation, multi-step agents, and tool use.
  • 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, vector databases, and distributed data and compute tools such as Kafka, Airflow, or Spark.
  • Contributions to open-source AI or distributed-systems projects.

About the Company

cb

PagerDuty

Real-time incident management and on-call platform

What PagerDuty does: PagerDuty provides an incident management platform that helps organizations detect and resolve IT issues quickly to minimize disruption. How its product works: It integrates with monitoring tools and IT systems to detect incidents in real time, then sends alerts to the right people, enforces on-call rotations, and guides incident resolution through automated workflows and escalations. How it differentiates from competitors: It focuses on on-call management and real-time incident response across many integrations, offering a scalable, subscription-based platform with configurable alerting, escalation policies, and professional services to support faster recovery. What the company's goal is: To reduce downtime and maintain the reliability and performance of digital services for organizations across industries by providing reliable, scalable incident management.

Company size
1,001-5,000
Company stage
IPO
Headquarters
San Francisco, CA
Founded
2009

Recently Posted Jobs

Explore more opportunities at PagerDuty

See more jobs