ML Infrastructure Engineer — From Research to Production

Acceler8 Talent; Cambridge (MA); Hybrid; USD 150,000 - 190,000; Full time

Job summary

Acceler8 Talent is seeking a Member of Technical Staff - ML Engineer in Cambridge, MA, with a hybrid arrangement (three days per week). You will translate research code into reliable services and build scalable ML infrastructure to support training, inference, and experimentation.

Join a small, high-caliber team with backgrounds at NVIDIA and Google, and own critical systems used by researchers and product teams.

Qualifications

• 3+ years operating production ML training or inference infrastructure
• Depth in one area: training, model serving, ML platforms or agent/gateway/evaluation infra
• Experience turning research code into tested services and resolving production failures

Responsibilities

• Turn research code into reliable services and build the ML infrastructure that makes it possible
• Collaborate with researchers and technical leadership to own critical systems
• Diagnose and resolve production issues to maintain reliability and performance

Skills

Production ML infra

Software engineering

Troubleshooting prod failures

Tools

CUDA

Cloud infrastructure

Job description

Acceler8 Talent is seeking a Member of Technical Staff - ML Engineer in Cambridge, MA, with a hybrid arrangement (three days per week). You will translate research code into reliable services and build scalable ML infrastructure to support training, inference, and experimentation.

Join a small, high-caliber team with backgrounds at NVIDIA and Google, and own critical systems used by researchers and product teams.