Senior AI/ML Engineer: Production-Scale LLM Agents

PagerDuty; Lisboa; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Company equity

ESPP (Employee Stock Purchase Program)

Retirement plan

Paid vacation time

Paid holidays and sick leave

Wellness days & HibernationDuty

Job summary

PagerDuty is seeking a Senior AI/ML Engineer to design and ship AI systems at scale, powering Incident Management AI Agents and LLM-powered capabilities across the PagerDuty Platform. You will own the full lifecycle from framing problems to reliable serving in production.

The role emphasizes passion for modern AI, LLMs, agents, and retrieval, guided by reliability and high-throughput systems. Hybrid work model with global offices supports collaboration across teams.

Qualifications

• 5+ years of software engineering with production distributed systems experience.
• Hands-on experience shipping AI systems in production (LLM-powered apps, agents, or retrieval).
• Strong fundamentals and ability to move between systems and AI code.
• Grounding in prompting, retrieval, agents, and evaluating LLM behavior.

Responsibilities

• Design and build AI-powered features like LLM agents, retrieval, and event intelligence for high-volume streams.
• Architect and own agent orchestration, retrieval pipelines, tool integrations, and low-latency inference at scale.
• Ensure reliability, throughput, and fault tolerance across services under bursty load.
• Move AI features from prototype to production with evaluation, guardrails, observability, and improvement loops.
• Collaborate with platform, product, and research teams to define success and integrate AI into existing services.

Skills

5+ years software eng

Production AI systems

Programming fundamentals

Applied AI fundamentals

Cloud infra (AWS/GCP/Azure)

Kubernetes

Communication skills

LLM/retrieval/agents

Tools

LangChain

LlamaIndex

Kafka

Airflow

Spark

Job description

PagerDuty is seeking a Senior AI/ML Engineer to design and ship AI systems at scale, powering Incident Management AI Agents and LLM-powered capabilities across the PagerDuty Platform. You will own the full lifecycle from framing problems to reliable serving in production.

The role emphasizes passion for modern AI, LLMs, agents, and retrieval, guided by reliability and high-throughput systems. Hybrid work model with global offices supports collaboration across teams.