SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
PagerDuty is a leader in Digital Operations Management, trusted by over 13,000 organizations including 60 Fortune 100 companies. The company's Operations Cloud ingests billions of signals and converts them into real-time action for thousands of customers.
You will join the AI/ML engineering team to build and ship AI systems running in production at PagerDuty's scale. This role focuses on the intersection of large-scale distributed systems and machine learning, specifically powering Incident Management AI Agents, event intelligence, and LLM-powered capabilities across the platform.
Key responsibilities include:
- Contributing to AI-powered features including LLM agents, retrieval systems, and event intelligence operating on high-volume, real-time data
- Building and maintaining systems behind these features: prompt and agent orchestration, retrieval pipelines, tool/API integrations, and inference services
- Writing production code, adding tests, and improving observability
- Learning to reason about latency, throughput, cost, and reliability of LLM-powered services
- Taking AI features from prototype toward production, supporting evaluation and monitoring loops
- Partnering with platform, product, and applied-research teams to turn requirements into working code
- Growing through code review, pairing, and mentorship
Required qualifications:
- 2+ years of software engineering experience building and shipping production software
- CS degree or equivalent practical experience
- Solid programming fundamentals and comfort moving between application and AI/model code
- Hands-on experience with modern AI (LLMs, prompting, retrieval, or agent frameworks)
- Exposure to distributed systems and how software runs reliably at scale
- Strong communication and collaboration skills
Nice-to-have skills include cloud infrastructure experience (AWS, GCP, Azure), containers, Kubernetes, familiarity with LLM ecosystems (LangChain, LlamaIndex, vector databases, Kafka, Airflow), interest in agentic systems and LLM evaluation, and open-source contributions.
PagerDuty operates a hybrid work model with offices in 8 major cities including Lisbon. The company values potential and encourages applications even if candidates don't meet every requirement.
