Mandarin-Speaking FDE: Inference & Post-Training

Fdetimes; Singapore; Remote; SGD 140,000 - 230,000; Full time

Job summary

Together AI, the AI Native Cloud, is seeking a Forward Deployed Engineer to partner with production AI teams, optimize inference, and guide deployment for high-impact POCs. You will work hands-on with open-source LLMs, orchestrate post-training workflows, and collaborate with SAs, CX, and Sales to ensure success across top accounts.

Based in Singapore with flexible remote work, you will influence platform design through field learnings and help customers realize time-to-value from the first day

Qualifications

• 5+ years in a technical role with focus on inference systems, open-source LLM deployment, or post-training workflows.
• Expert-level experience with inference engines (e.g., vLLM, TensorRT-LLM, SGLang) and diagnosing performance issues.
• Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, and quantization techniques.

Responsibilities

• Inference Engine Optimization: Select, configure, and optimize inference engine based on hardware, model architecture, and workload profile.
• Configuration & Performance Tuning: Develop updates to win POCs, benchmarks, and optimize deployments; tune KV cache, speculative decoding, tensor parallelism, and quantization.
• Post-Training & Fine-Tuning: Drive RL training runs and optimize system design; guide customers through LoRA, SFT, DPO, RLHF, GRPO pipelines.
• Strategic Customer Alignment: Act as primary technical contact for aligned strategic accounts, monitor configurations, and optimize to meet milestones.
• Onboarding Alignment: Ensure right inference and post-training configurations from day one.
• Product Feedback Loop: Influence roadmap by surfacing field insights and drive feature adoption with strategic logos.

Skills

Inference systems

Open-source LLM deployment

Post-training workflows

Python programming

Production experience

Tools

vLLM

TensorRT-LLM

SGLang

Job description

Together AI, the AI Native Cloud, is seeking a Forward Deployed Engineer to partner with production AI teams, optimize inference, and guide deployment for high-impact POCs. You will work hands-on with open-source LLMs, orchestrate post-training workflows, and collaborate with SAs, CX, and Sales to ensure success across top accounts.

Based in Singapore with flexible remote work, you will influence platform design through field learnings and help customers realize time-to-value from the first day