Senior Machine Learning Infrastructure Engineer (AI)

TL;DR

Senior Machine Learning Infrastructure Engineer (AI): Building and evolving robust ML infrastructure at scale with an accent on feature stores, LLM serving, and model deployment platforms. Focus on designing highly efficient serving systems using Ray Serve and Triton to enable large-scale machine learning across global hirify.global products.

Location: Must be based in or able to work from Palo Alto, CA (Hybrid: 3 days/week in-office required)

Salary: $220,000–$250,000 per year

Company

hirify.global is a global leader in social discovery, connecting millions of users across 190 countries through high-scale machine learning-powered features.

What you will do

• Design, build, and operate production-grade ML serving infrastructure using Ray Serve and Triton.
• Develop and maintain specialized infrastructure for serving large language models (LLMs).
• Build the foundation of a scalable feature store using Databricks and internal tooling.
• Partner with ML engineers and CloudOps to accelerate model iteration and production deployment velocity.
• Own infrastructure projects end-to-end, from architectural design to implementation and adoption.
• Establish and propagate best practices in MLOps and distributed systems across the organization.

Requirements

• Bachelor’s degree in Computer Science, Engineering, or a related field.
• 5+ years of experience building or operating ML platforms, including training, serving, and feature management.
• Strong software engineering fundamentals with proficiency in Python and at least one of Java, Scala, or Go.
• Hands-on experience with ML serving platforms such as Triton, Ray Serve, or Seldon.
• Deep experience in distributed systems, cloud infrastructure, and modern deep learning architectures.
• Proven ability to bridge the gap between research and reliable production-grade systems.

Nice to have

• Experience working in large-scale consumer product environments.
• Direct experience building feature stores from the ground up.
• Background in optimizing performance for transformer-based models.

Culture & Benefits

• Collaborative team environment operating across multiple functions and time zones.
• Commitment to diversity, equity, and inclusion with a focus on celebrating unique perspectives.
• Culture that encourages taking risks, sharing honest feedback, and learning from mistakes.
• Emphasis on professional development through mentorship and technical knowledge sharing.
• Opportunity to impact core user experiences for approximately 50 million monthly users.