Inference Platform Engineer for Open-Source Models

Together AI; San Francisco (CA); On-site; USD 200,000 - 290,000; Full time

Benefits offered by this job

Health insurance

Startup equity

Job summary

Together AI in San Francisco is seeking a Research Engineer to help build a platform that lets users customize open-source models, bridging post-training and production inference. You will contribute across Fine-Tuning, RL, and Evaluation services and collaborate with product, research, and engineering teams to keep the API reliable and scalable.

This full-time role offers a competitive US salary range and equity, with focus on building foundational AI infrastructure for developers worldwide.

Qualifications

• 2+ years of experience building and deploying machine learning-based services in production environment.
• Hands-on experience with modern inference engines (SGLang, vLLM, TensorRT-LLM).
• Familiar with fine-tuning LLMs and other AI models.

Responsibilities

• Design and build Together’s systems for customizing open-source models.
• Build integrations between the Model Shaping and Inference platforms for seamless post-training to production serving.
• Add features to inference engines for large-scale post-training experiments and RL workload optimizations.
• Ensure the service is stable, with on-call rotation and 24/7 platform availability.

Skills

ML services

Inference engines

Python

Go

LLMs fine-tuning

Tools

SGLang

vLLM

TensorRT-LLM

Job description

Together AI in San Francisco is seeking a Research Engineer to help build a platform that lets users customize open-source models, bridging post-training and production inference. You will contribute across Fine-Tuning, RL, and Evaluation services and collaborate with product, research, and engineering teams to keep the API reliable and scalable.

This full-time role offers a competitive US salary range and equity, with focus on building foundational AI infrastructure for developers worldwide.