Senior ML Infrastructure Engineer — Production Inference

HellaGoodAudio; United States; A distancia; USD 187.000 - 243.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health insurance

Stock options

Retirement plans

Generous vacation and personal days

Parental leave

Descripción de la vacante

Unity Technologies seeks a Senior ML Engineer to design and evolve an online model inference platform, building reliable production infrastructure for serving ML models with low latency and high reliability on high-traffic systems.

You will shape packaging, validation, monitoring, and deployment workflows, collaborating with ML engineers and platform teams to scale, monitor, and iterate in production while maintaining safety and cost efficiency.

Formación

• Experience building and operating production-grade online ML inference systems.
• Experience with model serving frameworks such as NVIDIA Triton Inference Server, TorchServe, Ray Serve, TensorFlow Serving.
• Experience optimizing inference workloads (quantization, dynamic batching, GPU acceleration, runtime tuning).
• Strong experience with distributed systems, Kubernetes, autoscaling, service reliability and observability.
• Strong Python programming skills for production ML systems and high-scale services.
• Experience with PyTorch and modern model deployment workflows (packaging, validation, serving lifecycle).
• Experience designing infrastructure for safe model rollout (canary testing, A/B, automated rollback).
• Strong systems thinking about latency, throughput, reliability, scalability and cost tradeoffs.
• Proven ability to lead technical direction and influence architectural decisions.

Responsabilidades

• Design and operate large-scale online inference infrastructure with low latency and high reliability.
• Develop infrastructure for distributed training workflows (PyTorch, Ray Data, Ray Train).
• Integrate ML pipelines with workflow orchestration (Flyte, Airflow).
• Optimize model performance via compilation, GPU/CPU utilization, scheduling, and tuning.
• Improve observability of ML systems (latency, throughput, errors, cost).
• Collaborate with ML engineers to enable rapid model iteration safely and scalably.
• Improve reliability and reproducibility of serving workflows (packaging, validation, deployment automation).
• Lead architectural improvements for a robust, scalable, cost-efficient platform.

Conocimientos

ML inference systems

Python programming

Distributed systems

Model deployment workflows

Canary/A/B testing

System architecture leadership

Herramientas

NVIDIA Triton Inference Server

TorchServe

Ray Serve

TensorFlow Serving

PyTorch

Kubernetes

Descripción del empleo

Unity Technologies seeks a Senior ML Engineer to design and evolve an online model inference platform, building reliable production infrastructure for serving ML models with low latency and high reliability on high-traffic systems.

You will shape packaging, validation, monitoring, and deployment workflows, collaborating with ML engineers and platform teams to scale, monitor, and iterate in production while maintaining safety and cost efficiency.