Senior AI Infrastructure Engineer, LLM/AI Platforms

This is a fully remote position, open to applicants in United States.

📋 Description

• Provision and configure extensive GPU clusters and computing resources for training, fine-tuning, and inference workloads of large language models (LLMs).

• Develop and enhance model-serving infrastructure for LLMs, focusing on the deployment and optimization of various inference frameworks.

• Oversee model lifecycle management, including version control, checkpointing, and ensuring reproducibility across both training and inference deployments.

• Design and advocate for robust evaluation frameworks to measure model performance, accuracy, and reliability, ensuring AI systems consistently meet production-ready standards.

• Identify and resolve bottlenecks related to GPU utilization and memory efficiency, employing techniques such as quantization, batching, and caching.

• Architect and sustain data platforms and pipelines tailored for LLMs, Retrieval-Augmented Generation (RAG), and AI Agentic Systems at scale.

• Deliver high-quality production-ready code with an emphasis on performance, maintainability, and rigorous testing, ensuring rapid deployment without sacrificing quality.

• Utilize expertise in data modeling, normalization, and semantic cataloging to support AI/ML workloads.

• Establish and enforce best practices for MLOps/DataOps related to LLMs, including monitoring, observability, and zero-touch recovery mechanisms for AI services.

• Thoroughly document architectural designs and clearly communicate technical decisions to stakeholders.

• Collaborate with Data Scientists, Product Managers, and various engineering teams across the organization to turn research prototypes into robust, production-grade services.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Data Engineering, or a related STEM field; Master’s degree is preferred.

• A minimum of 6 years of experience in Infrastructure/Data Engineering, with at least 2 years dedicated to building and maintaining platforms/pipelines that support LLM-based systems and applications.

• Proven hands-on experience in LLM infrastructure engineering, including cluster provisioning, optimizing training workloads, and maintaining inference pipelines.

• Exceptional proficiency in writing clean, elegant, performant, and thoroughly tested code, along with a strong focus on prompt action and delivering results.

• Deep understanding of engineering practices, including effective peer code reviews and resilient architectural design.

• Demonstrated technical leadership and mentoring capabilities.

• Documented experience in leveraging AI technologies to enhance decision-making, streamline workflows and processes, improve efficiency, and drive business outcomes.

🏝️ Benefits

• Market leader in compensation and equity awards.

• Comprehensive physical and mental wellness programs.

• Competitive vacation and holidays for recharging.

• Paid parental and adoption leaves.

• Professional development opportunities available for all employees, regardless of level or role.

• Employee Networks, geographic neighborhood groups, and volunteer opportunities to foster connections.

• Vibrant office culture featuring world-class amenities.

• Great Place to Work Certified™ across the globe.