jobs

Forward Deployed Engineer (Inference & Post-Training) - Mandarin Speaking

About the role As a Forward Deployed Engineer (FDE) focused on Inference & Post-Training, you will be a hands-on technical partner to our most strategic customers — production AI teams looking to leverage high quality models and do inferenc

Company

Together AI

Location

Singapore

Status

Open

Posted

2026-08-04T22:25:34+00:00

A forward deployed engineer at Together AI in Singapore, onsite with strategic customers. The work is hands-on: selecting and tuning inference engines (vLLM, TensorRT-LLM, SGLang), tuning KV cache, speculative decoding, tensor parallelism and quantization, and guiding fine-tuning and RL pipelines — LoRA, SFT, DPO, RLHF, GRPO. The posting calls the role a deep-domain specialist alongside solutions architects, not their replacement, feeding field insights into the product and model roadmap. It wants five-plus years in inference systems, open-source LLM deployment or post-training, strong Python, and Singapore citizenship or permanent residency.