Inference Platform Engineer for Open-Source ML

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

Benefits offered by this job

Startup equity

Health insurance

Job summary

Together AI is seeking a Research Engineer for the Model Shaping team to build a platform that lets users tailor open-source models with their data. You will work across training and inference, enhancing Fine-Tuning, RL, and Evaluation services, and ensuring reliable, scalable API integration into our infrastructure.

You will collaborate with product, research, and engineering teams to advance open-source AI tooling, supporting developers worldwide in creating high-quality, task-specific models

Qualifications

• Experience building and deploying ML services in production environments.
• Strong software engineering background in Python or Go.
• Familiarity with fine-tuning LLMs and ML models.
• Ability to stay current with ML research and industry trends.

Responsibilities

• Design and build systems for customizing open-source models.
• Integrate Model Shaping and Inference platforms for seamless post-training to serving.
• Add features to inference engines to optimize RL workloads.
• Participate in on-call rotation to ensure 24/7 platform availability.

Skills

ML service development

Python

Go

Tools

SGLang

vLLM

TensorRT-LLM

Job description

Together AI is seeking a Research Engineer for the Model Shaping team to build a platform that lets users tailor open-source models with their data. You will work across training and inference, enhancing Fine-Tuning, RL, and Evaluation services, and ensuring reliable, scalable API integration into our infrastructure.

You will collaborate with product, research, and engineering teams to advance open-source AI tooling, supporting developers worldwide in creating high-quality, task-specific models