Senior MLOps Engineer

Later•Vancouver, BC
•$125,000 - $205,000

About The Position

Later is hiring a Senior MLOps Engineer to build and scale infrastructure that moves machine learning and AI systems from prototype to production. The role owns pipelines for training, retraining, deploying, and serving models—including forecasting, recommendation, LLM-based, and agentic features—across AWS and GCP. It sits on the Infrastructure team, partnering with DevOps, Data Science, Data Engineering, Platform, and Product Engineering. Initially, work is expected to be split roughly equally between ML platform work and shared infrastructure, with the focus shifting toward ML as the practice grows. The work is primarily infrastructure and automation, with hands-on coding as needed. The engineer will lead MLOps strategy and architecture, select and evaluate tooling, and build and operate production ML infrastructure and workflows. This includes automated model training and retraining, deployment and rollback, LLM inference, cloud and GPU infrastructure, training-data pipelines, monitoring, model versioning, and reproducible training. The role also establishes standards, documentation, and self-service guidance; leads incident reviews; mentors engineers; and communicates technical tradeoffs to technical and non-technical stakeholders. Success in the first 30 days includes learning the cloud, Kubernetes, CI/CD, data, and ML platforms and identifying major gaps. By 60 days, the engineer is expected to own improvements across infrastructure and automation, deployment consistency, GPU provisioning and monitoring, alerting, and runbooks. By 90 days, success includes an automated production model deployment, retraining, and rollback pipeline; live drift, latency, and cost alerts; an initial MLOps roadmap reviewed with relevant leads; and security and compliance checks integrated into the ML deployment path.

Requirements

  • At least 7 years of DevOps, cloud, or software engineering experience in production environments, including technical leadership such as leading projects, setting direction, and mentoring; people management is not required.
  • Deep expertise with Kubernetes (EKS), Helm, and microservices, including running GPU workloads on Kubernetes.
  • Hands-on AWS experience and a track record of using Terraform for scalable, auditable infrastructure as code.
  • Experience deploying, serving, and scaling ML models in production, including CI/CD for ML.
  • Experience building data and training pipelines in partnership with Data Science and Data Engineering teams.
  • Strong system design skills, including designing ML systems end to end and explaining tradeoffs.
  • Clear communication with technical and non-technical audiences.

Nice To Haves

  • GCP experience, especially BigQuery.
  • Amazon SageMaker experience.
  • Experience with self-hosted LLM deployments on Kubernetes, such as vLLM or KServe.
  • Experience with orchestration and experiment tracking tools such as Airflow, Kubeflow, Argo Workflows, or MLflow.

Responsibilities

  • Own the MLOps roadmap with Infrastructure, Data Science, and Data Engineering leaders, aligned with product and AI growth plans.
  • Evaluate and select tooling for orchestration, model registry, experiment tracking, LLM serving, and observability; recommend whether to build or buy.
  • Shape the long-term architecture of the multi-cloud ML and data platform, accounting for scalability, security, and cost.
  • Design, build, and operate production infrastructure for deploying and scaling ML models using CI/CD, GitOps, Kubernetes, and orchestration tools.
  • Own automated training and retraining pipelines, including model registration, validation, deployment, and rollback, and agree on retraining cadence with Data Science.
  • Deploy and operate LLM inference using self-hosted or managed services, including GPU capacity, cost controls, and performance monitoring.
  • Manage training and inference infrastructure across AWS and GCP, including GPU workloads, using Terraform.
  • Partner with Data Engineering to source and prepare training data from BigQuery and S3 and build pipelines and light transformations as needed.
  • Monitor model performance, latency, data drift, cost, and resource usage using tools such as CloudWatch, Prometheus, and Grafana.
  • Support model versioning, experiment tracking, and reproducible training workflows.
  • Lead troubleshooting of complex production and deployment issues and participate in the Infrastructure on-call rotation.
  • Set and document standards for infrastructure-as-code, CI/CD, observability, secure deployment, and ML workflow automation.
  • Write runbooks and self-service guides to help Product and Data teams deploy, monitor, and troubleshoot independently.
  • Lead incident reviews and post-mortems to improve operations.
  • Mentor engineers through pairing, code review, and feedback.
  • Explain technical tradeoffs clearly to technical and non-technical stakeholders.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service