ML Engineer (LLM Deployment & GPU)

Position Overview

We are looking for an ML Engineer with hands-on experience in deploying large language models (LLMs) on GPU infrastructure. This role combines ML engineering with DevOps, focusing on scalable deployments, API integration, and optimization of LLM performance.

Key Responsibilities

• Deploy and optimize LLMs on GPU-based infrastructure.
• Build and manage APIs for model serving (Python-based).
• Implement CI/CD, monitoring, and scaling for ML models.
• Collaborate on prompt engineering and model optimization.
• Manage containerized workloads (Docker/Kubernetes).

Required Qualifications

• 4–5 years of ML/DevOps engineering experience.
• Strong in Python, APIs, and LLM architecture.
• Experience with GPU deployments and cloud platforms (AWS/GCP/Azure).
• Familiarity with prompt engineering and inference optimization.
• Machine Learning: 5 years of experience (Required).

Benefits & Additional Information

• Pay: $60.00 - $75.00 per hour
• Job Type: Full-time
• Expected Hours: 40 per week
• Location: In person; Ability to Relocate: Phoenix, AZ 85003 (Relocate before starting work)