🛠 Tech Stack

💼 About This Role

You'll build ML training and inference pipelines for a healthcare AI platform that reduces patient delays. Your work will ensure robust, scalable model deployment and rapid iteration on cutting-edge VLMs and LLMs.

🎯 What You'll Do

• Architect and implement ML software systems for model deployment at scale
• Develop and maintain ML infrastructure including data pipelines and model evaluations
• Collaborate with ML and software engineers for seamless model integration
• Troubleshoot production issues and improve system performance

📋 Requirements

• 5+ years experience in ML model deployment and scaling in production
• Proficiency in Python and TypeScript
• Experience with software design for highly available ML systems
• Knowledge of observability tools for logging, metrics, and monitoring

✨ Nice to Have

• Experience with ML CI/CD and frameworks like PyTorch or TensorFlow
• Experience with inference frameworks like vLLM or TensorRT
• Experience with GPU orchestration and optimization

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 100% paid employee health benefit options
• 💰 Employer-funded 401(k) match
• 🍽️ Free lunch and snacks
• 🏢 Chelsea office with collaborative environment