ML Platform Lead Engineer: Scale Training & Inference

Paramount Group; Burbank (CA); On-site; USD 157,000 - 235,000; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Vision benefits

401(k) plan

Life insurance

PTO

Job summary

Paramount Global is seeking a Senior Lead ML Platform Engineer to architect and own the training and inference infrastructure for high-scale ML deployments. You will drive the adoption of AnyScale (Ray) and manage a Kubernetes-based inference environment to deliver sub-millisecond latency at scale.

You will lead cross-team initiatives, optimize GPU utilization across A100/H100/T4 instances, and mentor engineers, shaping the standard for ML deployments across the organization.

Qualifications

• 6-8+ years of experience in ML infrastructure or high-scale backend engineering.
• Extensive Kubernetes experience and serving frameworks for large-scale ML models.
• Strong knowledge of GPU architecture, CUDA, and optimizing ML workloads for hardware acceleration.
• Leadership roles across multiple teams (IC4/5) to drive technical direction.

Responsibilities

• Own long-term architectural direction for the Training and Inference.
• Lead Ray/AnyScale implementation for unified compute.
• Design and maintain K8s-based inference servers optimized for GPU memory and throughput.
• Navigate GPU instances trade-offs to optimize cost and performance.
• Standardize CI/CD, model versioning, and canary deployments.
• Define SLIs/SLOs to ensure reliability across the platform.
• Mentor senior engineers across ML Platform and Applied ML pods.

Skills

Kubernetes (K8s)

GPU architecture

Leadership (IC4/5)

Python & C++

Tools

AnyScale/Ray

Triton

TorchServe

Prometheus/Grafana

Job description

Paramount Global is seeking a Senior Lead ML Platform Engineer to architect and own the training and inference infrastructure for high-scale ML deployments. You will drive the adoption of AnyScale (Ray) and manage a Kubernetes-based inference environment to deliver sub-millisecond latency at scale.

You will lead cross-team initiatives, optimize GPU utilization across A100/H100/T4 instances, and mentor engineers, shaping the standard for ML deployments across the organization.