Research Engineer (Post-Training Inference)

Join Together, a leading company in the open-source AI ecosystem. As a Research Engineer, you will develop a platform for customizing open-source models, improve our Fine-Tuning, Reinforcement Learning, and Evaluation services, and collaborate with product, research, and engineering teams. You will also ensure the stability and robustness of our service. Enjoy competitive health insurance, flexible time off, and a supportive work environment.

• Develop a platform that enables users to customize open-source models with their own data.
• Build and improve Fine-Tuning, Reinforcement Learning, and Evaluation services, ensuring a seamless path from post-training to production serving.
• Collaborate closely with product, research, and engineering teams to keep the API reliable, performant, and well integrated into the company's technical infrastructure.
• Are familiar with the latest methods for fine-tuning LLMs and other AI models
• Have hands-on experience with modern inference engines, such as SGLang, vLLM, and TensorRT-LLM
• Have 2+ years of experience building and deploying machine learning-based services in a production environment
• Have a strong software engineering background in Python or Go
• Stay up to date with the latest advances and trends in the machine learning community
• Managing machine learning workloads on Kubernetes clusters
• Maintaining or contributing to open-source ML projects
• Developing large-scale and high-load production systems
• Developing CUDA/Triton/CuTE DSL kernels for inference
• Optimizing the performance of RL training workloads
• Serving low-precision (FP4/FP8) models, multiple LoRA adapters within one model instance (Multi-LoRA), or models distributed across several GPU nodes