Role overview

AI71 is seeking an MLOps Engineer to lead machine learning infrastructure and reliability strategy across the company’s platform. In this role, you will own the architecture for deploying, fine-tuning, and serving large language models and deep learning systems at scale, working across both cloud-based SaaS and on-premises deployments. You will mentor senior engineers, drive multi-quarter infrastructure initiatives, and serve as a force multiplier across AI71’s engineering organization.

Key responsibilities

Design and implement ML infrastructure architecture including model deployment strategies, pipeline engineering systems, and cloud-native infrastructure across AWS, Azure, and GCP.
Establish reliability standards for ML systems by defining monitoring approaches, performance targets for latency and throughput, and incident response procedures across research and production environments.
Mentor senior MLOps engineers and raise operational standards across multiple teams through technical leadership and knowledge sharing.
Lead cross-team initiatives to improve inference performance and reduce costs, including work with distributed training frameworks and optimization techniques.
Partner with ML researchers, product teams, and engineering leadership to develop and execute long-term ML infrastructure strategy.
Ensure ML infrastructure scales reliably in both managed SaaS and fully disconnected on-premises deployment models.

Requirements

At least 10 years of experience in MLOps, ML infrastructure, or machine learning engineering with demonstrated architectural ownership across large projects.
Proven success architecting large-scale model deployments including large language models and ML infrastructure systems in production environments.
Deep expertise with major cloud platforms (AWS, Azure, or GCP) and strong proficiency in Python.
Track record of mentoring engineers who have advanced to operate independently at higher levels of responsibility.
Architectural experience building ML systems that function reliably in both managed SaaS and air-gapped on-premises environments.
Kubernetes expertise at an architectural level, including GPU scheduling, multi-tenancy patterns, operators, and failure mode understanding in distributed clusters.
Strong communication and stakeholder management capabilities with demonstrated commitment to building diverse and inclusive engineering teams.

What makes this role worth considering

This position offers the opportunity to work on cutting-edge AI applications with a talented team solving real-world challenges in critical sectors. You will have access to world-leading models and resources while building foundational ML infrastructure at a mission-driven organization, with competitive compensation, significant career growth potential, and a flexible working environment equipped with the latest technologies.