Unity Software

22 hours ago

Senior Machine Learning Engineer, ML Infrastructure- Online

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Design and evolve an online machine learning inference platform for Unity Vector, building production-grade infrastructure that delivers low-latency, high-reliability model serving at scale. You’ll optimize inference performance, integrate training and serving pipelines with orchestration systems, and strengthen observability and monitoring. Partner across ML, platform, and product teams to enable safe experimentation (canary/A-B) and drive architectural improvements for robust, scalable, cost-efficient deployments.

Location: Seattle

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Design and operate large-scale online inference infrastructure to serve production ML models with low latency and high reliability.
•Develop infrastructure for distributed training workflows using tools like PyTorch and Ray (including Ray Data and Ray Train).
•Integrate ML pipelines with orchestration systems such as Flyte or Airflow for reliable multi-stage training workflows.
•Improve model performance and runtime efficiency via compilation, GPU/CPU utilization improvements, request scheduling, kernel fusion, and tuning.
•Enhance observability and reliability of ML serving by monitoring latency/throughput/error-rate/cost/saturation and improving packaging, validation, compatibility testing, and deployment automation.

Pay and Benefits

Salary: USD 187,200 - 243,300 annually

Equity and Bonus:Equity

Perks:Health InsuranceLife InsuranceDisability InsuranceCommuter BenefitsRetirement PensionPaid LeaveFamily-care ProgramsEmployee Assistance

Key Requirements

•Experience building and operating production-grade online ML inference systems such as NVIDIA Triton Inference Server, TorchServe, Ray Serve, or TensorFlow Serving.
•Strong experience optimizing inference workloads using techniques like dynamic batching, model compilation, quantization, GPU acceleration, and runtime tuning.
•Hands-on distributed systems experience with Kubernetes, autoscaling, service reliability, and production observability.
•Strong programming skills in Python with practical experience on production ML systems and high-scale services.
•Experience designing infrastructure for safe model rollout, including canary testing, A/B experimentation, and automated rollback.

Experience:Machine learningProduction ML

Skills:Systems thinkingTechnical leadershipArchitectural influence

Languages:English

Tech Stack:PythonPyTorchTriton Inference ServerKubernetesGKERayTorchServeTensorFlow ServingRay DataRay TrainFlyteAirflowGPUDynamic batchingModel compilationQuantizationKernel fusionCachingRuntime tuningAutoscaling

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Unity Software

Develops the Unity real-time 3D development platform used to create, operate, and monetize interactive experiences and games across mobile, console, PC, and AR/VR platforms. Serves developers, studios, and enterprises worldwide.

Industry: Developer Tools

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: San Francisco, United States

Founded: 2004

Glassdoor: 3.8

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Unity Software

22 hours ago

Senior Machine Learning Engineer, ML Infrastructure- Online

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 22 hours agoStatus: Live

Job Summary

Location: Seattle

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Design and operate large-scale online inference infrastructure to serve production ML models with low latency and high reliability.
•Develop infrastructure for distributed training workflows using tools like PyTorch and Ray (including Ray Data and Ray Train).
•Integrate ML pipelines with orchestration systems such as Flyte or Airflow for reliable multi-stage training workflows.
•Improve model performance and runtime efficiency via compilation, GPU/CPU utilization improvements, request scheduling, kernel fusion, and tuning.
•Enhance observability and reliability of ML serving by monitoring latency/throughput/error-rate/cost/saturation and improving packaging, validation, compatibility testing, and deployment automation.

Pay and Benefits

Salary: USD 187,200 - 243,300 annually

Equity and Bonus:Equity

Perks:Health InsuranceLife InsuranceDisability InsuranceCommuter BenefitsRetirement PensionPaid LeaveFamily-care ProgramsEmployee Assistance

Key Requirements

•Experience building and operating production-grade online ML inference systems such as NVIDIA Triton Inference Server, TorchServe, Ray Serve, or TensorFlow Serving.
•Strong experience optimizing inference workloads using techniques like dynamic batching, model compilation, quantization, GPU acceleration, and runtime tuning.
•Hands-on distributed systems experience with Kubernetes, autoscaling, service reliability, and production observability.
•Strong programming skills in Python with practical experience on production ML systems and high-scale services.
•Experience designing infrastructure for safe model rollout, including canary testing, A/B experimentation, and automated rollback.

Experience:Machine learningProduction ML

Skills:Systems thinkingTechnical leadershipArchitectural influence

Languages:English

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Unity Software

Industry: Developer Tools

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: San Francisco, United States

Founded: 2004

Glassdoor: 3.8

Website LinkedIn