Senior Machine Learning Infrastructure Engineer

2 weeks ago
Full-time
Senior
DevOps and Infrastructure
Unity

Unity

Unity is the top platform for real-time 3D content creation, empowering creators across industries to bring their ideas to life with interactive 2D and 3D content.

Internet Software & Services
5K-10K
Founded 2004

Description

  • Design, build, and maintain infrastructure that serves machine learning models in real time across Unity's ads ecosystem.
  • Build and operate scalable model serving pipelines in a high-QPS production environment.
  • Own latency, throughput, and reliability for production ML serving systems.
  • Partner with ML engineers to productionize models, manage deployments, and improve iteration speed.
  • Improve the observability, performance, and cost-efficiency of ML serving infrastructure.
  • Contribute to architectural decisions around feature serving, model versioning, and inference optimization.

Requirements

  • Experience building and operating ML infrastructure or model serving systems in production.
  • Proficiency in Golang or Python.
  • Strong systems engineering fundamentals.
  • Hands-on experience with Kubernetes and container orchestration at scale.
  • Familiarity with ML serving frameworks such as Ray Serve, Triton, TorchServe, or similar.
  • Understanding of distributed systems, API design, and system reliability.
  • Strong collaboration and communication skills in a remote-first environment.
  • Experience with feature stores, feature pipelines, or online/offline feature serving (preferred).
  • Background in ad tech, real-time bidding, or programmatic advertising systems (preferred).
  • Familiarity with infrastructure-as-code tools such as Terraform, observability tooling like Prometheus, Grafana, or OpenTelemetry, and real-time data pipelines, caching layers, or low-latency serving systems (preferred).
  • Professional verbal and written English communication is required for frequent collaboration with global colleagues and partners.

Benefits

  • Gross pay salary range of $183,700 to $248,600 USD.
  • Comprehensive health, life, and disability insurance.
  • Commute subsidy.
  • Employee stock ownership.
  • Competitive retirement/pension plans.
  • Generous vacation and personal days.
  • Support for new parents through leave and family-care programs.
  • Mental health and wellbeing programs and support.
  • Training and development programs.
  • Volunteering and donation matching program.
  • Office food snacks.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Data/Infrastructure Advocate Engineer - US Remote

Hugging Face 51-250 IT Services

Hugging Face is hiring its first Data/Infrastructure Advocate Engineer to bridge technical data infrastructure work with the global community around the Hub, Xet storage, and open data workflows.

AWS Colab GitHub Machine Learning Pandas Python
1 hour, 18 minutes ago

Cloud Infrastructure Engineer – Multinational Digital Infrastructure

Anduril Industries 1K-5K Aerospace & Defense

Anduril Industries is hiring a Multinational Digital Infrastructure engineer to design and operate secure cloud environments for its Maritime and AUKUS missions across Australia and allied nations.

AWS Azure Cybersecurity DevSecOps
1 hour, 26 minutes ago

Cloud ML DevRel Engineer - EMEA remote

Hugging Face 51-250 IT Services

Hugging Face is hiring a Cloud ML DevRel Engineer to help promote and explain its ML Cloud partnerships and platform by educating the ML community on how to run training and inference workloads more efficiently on major cloud and accelerator infrastructure.

AWS Azure Cloudflare Docker GCP Generative AI GitHub Kubernetes Machine Learning Python
2 hours, 1 minute ago

Open-Source Machine Learning Engineer - US Remote

Hugging Face 51-250 IT Services

Hugging Face is hiring an Open-Source Machine Learning Engineer to improve widely used ML libraries and support a global community of builders, researchers, and contributors.

Deep Learning GitHub Machine Learning Python PyTorch TensorFlow Transformers
2 hours, 18 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers