Développeuse ou développeur côté serveur (backend) Staff — Systèmes d’inférence ML / Staff Backend Engineer, ML Inference Systems

Unity Technologies•Montreal, QC

About The Position

Each day, we enable billions of players to access their favorite games and experiences. Our Vector Gamer AI team is at the heart of this mission, managing ad ranking and bidding decisions across billions of daily impressions. This team is where large-scale machine learning and real-world impact converge. We are looking for a Staff Backend Engineer to design, build, and operate the infrastructure on which these models rely. The person selected for this role will design and operate the distributed systems that power billions of decisions every day, with a focus on the performance, reliability, and scalability of inference systems. Join us and help shape how billions of gaming experiences are discovered and monetized, and how creators are rewarded.

Requirements

5+ years designing, deploying, and maintaining distributed systems at scale
Expertise in Golang for building high-performance, low-latency backend infrastructure
Hands-on experience with cloud infrastructure on GCP and workload orchestration with Kubernetes
Strong grounding in monitoring and observability tooling, including Prometheus and Grafana
Experience in ad tech, recommender systems, real-time personalization, or other performance-critical domains
Familiarity with microservice architectures, containerization (Docker), and CI/CD best practices
Familiarity with machine learning platforms, workflows, and serving infrastructure
Sufficient knowledge of English for professional verbal and written exchanges

Nice To Haves

Experience with ML inference servers like NVIDIA Triton Inference Server
Familiarity with auction mechanics or bidding systems in an ad tech context

Responsibilities

Design, develop, and deploy production-grade backend services and distributed systems powering large-scale online model inference at billions of daily requests
Drive technical direction of our inference platform, with a focus on low-latency, high-throughput serving infrastructure
Partner with ML engineers to ensure online serving infrastructure scales with growing model complexity and inference volumes, without compromising latency or throughput
Ensure the reliability, scalability, and efficiency of our systems in production using monitoring and observability tools like Prometheus and Grafana
Manage and optimize cloud infrastructure on GCP, orchestrating workloads with Kubernetes across a high-scale production environment
Promote and implement best practices for backend service development, testing, deployment, and monitoring (DevOps, SRE)