Remote FDE: Inference & Post-Training

FDE Times; San Francisco (CA); Remote; USD 270,000 - 300,000; Full time

Benefits offered by this job

Startup equity

Health insurance

Flexible remote work

Job summary

Together AI, the AI Native Cloud, seeks a Forward Deployed Engineer focused on Inference & Post-Training to partner with strategic customers on high‑quality models and scalable inference. You will work with SAs and apply optimization, LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation to production, influencing platform deployment and customer success.

This role offers remote flexibility across the US, with a base salary and equity as part of a comprehensive compensation package.

Qualifications

• 5+ years in a technical role focusing on inference systems or post-training workflows.
• Expert-level experience with inference engines (e.g., vLLM, TensorRT-LLM, SGLang).
• Deep knowledge of KV cache tuning, speculative decoding, tensor and pipeline parallelism, and quantization.
• Hands-on experience with fine-tuning and post-training pipelines (LoRA, SFT, DPO, RLHF, GRPO).
• Broad knowledge of state-of-the-art open-source models and model selection for different workloads.
• Strong Python skills; production experience.

Responsibilities

• Optimize inference engines based on hardware, model, and workload.
• Develop config updates to win POCs, benchmarks, and optimize deployments; tune KV cache, speculative decoding, tensor and pipeline parallelism, and quantization.
• Drive post-training and fine-tuning with LoRA, SFT, DPO, RLHF, and GRPO; advise on system design.
• Act as the primary technical contact for aligned strategic accounts; optimize endpoint configurations and collaboration to hit milestones.
• Onboard customers with correct inference and post-training configurations from day one to improve time-to-value.
• Provide product feedback to influence roadmap and drive feature adoption with key logos.

Skills

Python

Production experience

LLM deployment

Inference systems

Tools

vLLM

TensorRT-LLM

SGLang

Job description

Together AI, the AI Native Cloud, seeks a Forward Deployed Engineer focused on Inference & Post-Training to partner with strategic customers on high‑quality models and scalable inference. You will work with SAs and apply optimization, LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation to production, influencing platform deployment and customer success.

This role offers remote flexibility across the US, with a base salary and equity as part of a comprehensive compensation package.