ML Ops Infrastructure Engineer (AI)

TL;DR

ML Ops Infrastructure Engineer (AI): Building and maintaining the critical CI/CD pipelines, deployment systems, and testing infrastructure to operationalize voice-native foundation models at scale with an accent on CI/CD design, model evaluation, and production reliability. Focus on solving complex concurrency and scaling challenges to ensure that research-to-production transitions are automated, robust, and performant.

Location: Remote (USA). International candidates may be hired via an Employer of Record (EoR) model where supported.

Salary: $160,000 – $220,000

hirify.global is a leading platform for the voice AI economy, providing real-time speech APIs used by over 200,000 developers and major organizations to build production-grade voice agents.

What you will do

• Design and build CI/CD pipelines for ML model development, validation, and production deployment.
• Architect and maintain model deployment pipelines that facilitate secure and reliable transitions from staging to production.
• Implement comprehensive monitoring for model performance, including accuracy, latency, drift detection, and regression alerts.
• Develop automated retraining pipelines triggered by data changes or performance degradation.
• Collaborate with research engineers to enforce model quality gates and optimize model serving infrastructure for throughput and cost.

Requirements

• 4+ years of experience in MLOps, DevOps, or infrastructure engineering focused on ML systems.
• Strong proficiency in Python with a focus on automation and workflow tooling.
• Deep experience building CI/CD pipelines for software and model delivery.
• Hands-on experience with Docker and Kubernetes for containerized workloads.
• Proven track record of deploying and serving ML models in production environments.

Nice to have

• Experience with model serving frameworks such as NVIDIA Triton, TensorRT, or ONNX Runtime.
• Background in speech, audio, or real-time media ML systems.
• Proficiency with Infrastructure as Code (Terraform or Pulumi).
• Experience with GPU-accelerated inference optimization and profiling.

Culture & Benefits

• Unlimited PTO and 12 paid US company holidays.
• Holistic health benefits including medical, dental, vision, and mental health support.
• 401(k) plan with company match.
• Stipends for personal productivity, home office upgrades, and continuous learning.
• Culture of high experimentation with AI tools and cross-team collaboration.