ML Systems Engineer — Production Training & Inference

Acceler8 Talent; Massachusetts; Hybrid; USD 180,000 - 240,000; Full time

Job summary

Acceler8 Talent in Cambridge, MA, is seeking a Member of Technical Staff, ML Engineer to join on a hybrid basis (3 days in office). The role focuses on turning research code into production systems and owning the training and inference infrastructure behind AI-driven discovery.

You will own distributed ML training and inference, build scalable services for experiments, and collaborate with researchers to push scalable AI solutions forward.

Qualifications

• 3+ years building and operating production ML training or inference infrastructure at scale.
• 3+ years of software engineering on systems used by researchers.

Responsibilities

• Translate research code into dependable services with clear interfaces, meaningful tests and operational ownership.
• Build services for launching experiments, routing across models and delivering results.
• Own distributed ML jobs, GPU scheduling and model serving on a shared engineering platform.
• Develop deep expertise in one area: distributed training, inference serving, ML platforms, or LLM gateway and agent infrastructure.

Skills

Distributed training

Inference serving

ML platforms

Gateways & agents

Job description

Acceler8 Talent in Cambridge, MA, is seeking a Member of Technical Staff, ML Engineer to join on a hybrid basis (3 days in office). The role focuses on turning research code into production systems and owning the training and inference infrastructure behind AI-driven discovery.

You will own distributed ML training and inference, build scalable services for experiments, and collaborate with researchers to push scalable AI solutions forward.