ML Ops Engineer (Medtech)

TL;DR

ML Ops Engineer (Medtech): Architecting and managing scalable machine learning and AI training/inference pipelines for an intelligent healthcare platform with an accent on robustness, production performance, and system efficiency. Focus on building foundational tooling for model evaluation, deployment, and monitoring to accelerate iteration on proprietary LLMs and VLMs.

Location: Must be able to work from the Chelsea office (New York, US) 4 days/week

Salary: $190K - $230K

Company

hirify.global builds AI-driven healthcare infrastructure that automates the processing of medical referrals, helping providers reduce delays and denials.

What you will do

• Architect and implement robust ML software systems for deploying models at scale.
• Develop and maintain infrastructure for data pipelines, model evaluations, and training.
• Build tooling for online and offline evaluation of ML and LLM systems.
• Collaborate with engineers to ensure seamless model integration with products.
• Monitor production model performance and perform incident response.

Requirements

• 5+ years of experience in ML model deployment, infrastructure, and scaling in production
• Strong software engineering fundamentals with Python and TypeScript
• Deep knowledge of observability, logging, and metrics
• Experience with distributed systems and reliability
• Ability to work in a fast-paced startup environment

Nice to have

• Experience with ML CI/CD and frameworks like PyTorch or TensorFlow
• Proficiency with inference frameworks like vLLM, TensorRT, or Triton
• Knowledge of GPU orchestration, scheduling, and cost management
• Experience with CUDA profiling and GPU optimization

Culture & Benefits

• High-caliber team with a Cowboy value system focused on speed and impact
• 100% paid employee health benefit options
• Employer-funded 401(k) match
• Unlimited PTO and competitive parental leave
• Free lunch and office snacks