Senior AI/ML Engineer: Scalable LLMs & Real-Time AI

Triwill Group; Lisbon (ME); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity

ESPP

Retirement plan

Vacation

Paid holidays

Wellness days

Parental leave

Volunteer time off

Hack weeks

Mental wellness programs

Job summary

PagerDuty is seeking a Senior AI/ML Engineer to design and ship production AI systems that scale across real-time incident management. You’ll own the lifecycle from problem framing to reliable serving, focusing on LLM-powered agents, retrieval, and event intelligence within a high-throughput platform.

You’ll partner with platform, product and research teams to define “good” AI and integrate it cleanly into existing services while maintaining reliability and observability in a fast-paced

Qualifications

• 5+ years of software engineering in distributed systems.
• Hands-on production AI systems experience (LLM-powered apps, agents, retrieval).
• Strong programming fundamentals across systems and AI code.
• Knowledge of prompting, retrieval, agent patterns, and guardrails for LLMs.
• Experience with cloud infra (AWS/GCP/Azure), containers, and orchestration (Kubernetes).
• Reliability-minded, scalable systems design with clear trade-offs.
• Excellent communication and collaboration.

Responsibilities

• Design and ship AI-powered features like LLM agents and retrieval in real-time streams.
• Architect and own prompts orchestration, retrieval pipelines, and low-latency inference at scale.
• Ensure consistency, throughput, fault tolerance, and cost across services.
• Move AI features from prototype to production with robust evaluation and observability loops.
• Collaborate with platform, product, and research teams to integrate AI into services.
• Mentor teammates and help shape the team's technical direction.

Skills

Distributed systems

Production AI

Cloud (AWS/GCP/Azure)

Kubernetes

Strong coding

Reliability mindset

Communication

Tools

LangChain

LlamaIndex

Kafka

Airflow

Spark

Job description

PagerDuty is seeking a Senior AI/ML Engineer to design and ship production AI systems that scale across real-time incident management. You’ll own the lifecycle from problem framing to reliable serving, focusing on LLM-powered agents, retrieval, and event intelligence within a high-throughput platform.

You’ll partner with platform, product and research teams to define “good” AI and integrate it cleanly into existing services while maintaining reliability and observability in a fast-paced