ML Inference Infrastructure Engineer — Scale & GPU

Talanto; Northern (KY); Hybrid; USD 221,000 - 260,000; Full time

Benefits offered by this job

Generous Time Off

Comprehensive Health Plans

Paid Parental Leave

Family Forming Benefits

401(k) Matching

Personal Device Allowance

Pre-tax Benefits

Lifestyle Wallet

Mental Health Support

Sabbatical Leave

Compensation and Equity

Job summary

Talanto in the United States is seeking an ML Infrastructure Engineer, Model Inference to build and optimize our core inference infrastructure powering AI models. You will work with Infrastructure and Research to deploy, optimize, and orchestrate AI models across scalable systems.

The role requires 5+ years in production ML, strong Kubernetes skills, and experience with model serving frameworks and GPU optimization. Hybrid options may apply with a focus on scalable backend infrastructure.

Qualifications

• 5+ years of experience building and deploying ML models in production.
• Deep understanding of container orchestration and distributed systems.
• Expertise in Kubernetes administration, CRDs, operators, and cluster management.

Responsibilities

• Design, deploy and maintain scalable Kubernetes clusters for AI model inference and training.
• Develop, optimize, and maintain ML model serving infrastructure with high performance and low latency.
• Scale backend infrastructure for AI-driven products, focusing on deployment and throughput.
• Optimize compute-heavy workflows and GPU utilization for ML workloads.
• Build a robust model API orchestration system.
• Collaborate with leadership to scale infrastructure as the company grows.

Skills

Container orchestration

Distributed systems

API development

Communication skills

Tools

Kubernetes

NVIDIA Triton Server

PyTorch

TensorFlow

Terraform

Ansible

GitOps

CUDA optimization

Job description

Talanto in the United States is seeking an ML Infrastructure Engineer, Model Inference to build and optimize our core inference infrastructure powering AI models. You will work with Infrastructure and Research to deploy, optimize, and orchestrate AI models across scalable systems.

The role requires 5+ years in production ML, strong Kubernetes skills, and experience with model serving frameworks and GPU optimization. Hybrid options may apply with a focus on scalable backend infrastructure.