ML Platform Lead Engineer, Training and 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

Select how often (in days) to receive an alert:

ML Platform Lead Engineer, Training and Inference

46353

Burbank, CA, US, 91505

Technology

Burbank

Full-Time

On-Site

#WeAreParamount on a mission to unleash the power of content… you in?
We’ve got the brands, we’ve got the stars, we’ve got thepowerto achieve our mission to entertain the planet – now all we’re missing is… YOU! Becoming a part of Paramount means joining a team of passionate people who not only recognize the power of content but also enjoy a touch of fun and uniqueness. Together, we co-create moments that matter – both for our audiences and our employees – and aim to leave a positive mark on culture.

Overview

We are seeking a Senior Lead / Lead ML Platform Engineer to architect and own the technical direction for our Training and Inference infrastructure. This is a high-leverage role designed for an expert who understands the deep technical stack required to shift ML models from research to global production. You will be responsible for the "engine room" of the AMLG, ensuring that our MLEs can train massive models efficiently and serve them with sub-millisecond reliability. This role requires a unique blend of expertise in distributed systems and hardware acceleration. You will lead the adoption and optimization of AnyScale (Ray) for distributed training and manage a high-performance Kubernetes-based inference environment. You aren't just managing clusters; you are building a seamless, scalable platform that abstracts the complexity of GPUs and distributed compute for the entire organization.

Why This Role Matters

The ML Platform Lead is the force-multiplier for every other ML pod. In this role, you will directly shape:

• The Training Foundation: Establishing AnyScale/Ray as the standard for distributed compute, enabling MLEs to train models on petabytes of data without managing infrastructure.
• Inference at Scale: Architecting the serving layer that handles billions of requests per day, optimizing for both p99 latency and GPU utilization.
• Operational Excellence: Setting the organizational standards for how ML models are deployed, monitored, and scaled across the enterprise.

Key Responsibilities

• Technical Roadmap & Strategy: Own the long-term architectural direction for the Training and Inference domains, ensuring the platform scales 10x over a 1–3 year horizon.
• Distributed Training Leadership: Lead the implementation and optimization of Ray/AnyScale, providing a unified compute layer for batch processing, model training, and reinforcement learning.
• High-Performance Inference: Design and maintain K8s-based inference servers (e.g., Triton, TorchServe, or vLLM) optimized for GPU memory management and high throughput.
• Hardware & Cost Optimization: Navigate the trade-offs between different GPU instances (A100s, H100s, T4s), optimizing for cost, availability, and performance.
• Cross-Team Standardization: Solve high-leverage problems that affect multiple pods (e.g., Entry, Session, Presentation), establishing reusable patterns for CI/CD, model versioning, and canary deployments.
• Reliability Engineering: Define and enforce SLIs/SLOs for the platform, ensuring that infrastructure failures never interrupt the user-facing personalization experience.
• Mentorship & Coaching: Act as a technical mentor to senior engineers across the ML Platform and Applied ML pods, raising the bar for system design and operational rigor.

Basic Qualifications

• 6-8+ years of experience in ML Infrastructure, Platform Engineering, or high-scale Backend Engineering.
• Orchestration & Serving: Extensive experience with Kubernetes (K8s) and serving frameworks for large-scale ML models.
• Hardware Proficiency: Strong knowledge of GPU architecture, CUDA, and optimizing ML workloads for hardware acceleration.
• Leadership (IC4/5): Proven track record of owning the technical direction for a major domain anddriving impact across multiple teams.

Preferred Qualifications

• Experience with Infra-as-Code (Terraform/Pulumi) and building automated MLOps pipelines.
• Distributed Systems Mastery: Deep expertise with Ray (AnyScale) or similar distributed compute frameworks.
• Familiarity with ML observability tools (Prometheus, Grafana, Weights & Biases, or MLFlow).
• Experience managing multi-cloud or hybrid-cloud ML environments.
• Deep knowledge of Python and C++ for performance-critical systems.

What Success Looks Like

• Unify the Compute Layer: Successfully transition the majority of AMLG training workloads to a governed AnyScale/Ray environment.
• Optimize Inference ROI: Measurably improve GPU utilization and reduce inference costs through better auto-scaling and server optimization.
• Establish Durable Standards: Author the "Gold Standard" for ML deployments that is adopted by at least three other pods in the organization.
• Reduce Systemic Risk: Implement a self-healing infrastructure layer that significantly reduces manual intervention for cluster-related failures.

Paramount Streaming, a division within Paramount Global, is the home to the company's direct-to-consumer services spanning free and paid in the form of Pluto TV and Paramount+. Pluto TV is the global leader in free ad-supported TV, delivering more than 1,400 global channels and an extensive library of streaming content, including live and original channels. Paramount+, digital subscription video-on-demand and live streaming service, combines live sports, breaking news, and A Mountain of Entertainment™. Paramount+ features an expansive library of original series, hit shows and popular movies across every genre from world-renowned brands and production studios, including SHOWTIME®.

ADDITIONAL INFORMATION

Hiring Salary Range: $157,000.00 - 235,000.00.

The hiring salary range for this position applies to New York, California, Colorado, Washington state, and most other geographies. Starting pay for the successful applicant depends on a variety of job-related factors, including but not limited to geographic location, market demands, experience, training, and education. The benefits available for this position include medical, dental, vision, 401(k) plan, life insurance coverage, disability benefits, tuition assistance program and PTO or, if applicable, as otherwise dictated by the appropriate Collective Bargaining Agreement.This position is bonus eligible.

What We Offer

• Attractive compensation and comprehensive benefits packages. Check out our full list of benefits here: https://www.paramount.com/careers/benefits
• Generous paid time off.
• An exciting and fulfilling opportunity to be part of one of Paramount’s most dynamic teams.
• Opportunities for both on-site and virtual engagement events.
• Unique opportunities to make meaningful connections and build a vibrant community, both inside and outside the workplace.
• Explore life at Paramount: https://www.paramount.com/careers/life-at-paramount

Skydance is an equal opportunity employer (EOE)

We embrace the opportunity to build a workforce that reflects a wide array of perspectives, backgrounds and experiences. Being an equal opportunity employer means that we take seriously our responsibility to consider qualified candidates on the basis of merit. In line with the laws of the country or region in which the role is based, this includes consideration without regard to race, color, ethnicity, national origin, citizenship status, religion or belief, sex, gender, gender identity or expression, sexual orientation, age, marital status, pregnancy, parenthood, physical or mental disability, genetic information, military or protected veteran status, union status or any other category protected by applicable law.

If you are a qualified individual with a disability, you may request a reasonable accommodation during the job application and/or recruitment process. You can request reasonable accommodations by calling 212.846.5500 or by sending an email to [e-mail]. Only messages left for this purpose will be returned.