jobapplier

Forward Deployed Engineer (Strategic Inference)

Together AI

Skills

Required

  • inference engines
  • KV cache tuning
  • speculative decoding
  • tensor parallelism
  • pipeline parallelism
  • quantization
  • Python
  • vLLM
  • TensorRT-LLM
  • SGLang

Preferred

  • open-source
  • open-source models
  • model selection
  • hardware profiles
  • inference systems
  • LLM deployment / post-training workflows
  • fine-tuning
  • LoRA
  • SFT

Join our team as a Forward Deployed Engineer (FDE) focused on Inference & Post-Training. In this role, you will be a hands-on technical partner to our most strategic customers, helping them leverage high-quality models and do inference at scale. You will work closely with our Solutions Architects and contribute to customer success, company growth, and the hardening of our core platform. Your responsibilities will include optimizing inference engines, developing configuration updates, driving post-training and fine-tuning, aligning with strategic customers, and providing product feedback.

Act as a hands-on technical partner to strategic customers, focusing on inference optimization, fine-tuning pipelines, and production deployment.

Responsibilities

  • Select, configure, and optimize inference engines based on hardware, model architecture, and workload profile; develop configuration updates to win critical POCs.
  • Drive hands-on RL training runs and optimize system design; guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation through production.
  • Post-Training Knowledge: Hands-on experience with fine-tuning and post-training pipelines, including LoRA, SFT, DPO, RLHF, and GRPO; ability to advise on system design

Requirements

  • Inference Optimization: Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, pipeline parallelism, and quantization techniques
  • Coding Proficiency: Strong Python skills; comfortable working in production environments
  • Inference Engine Depth: Expert-level, hands-on experience with inference engines (e.g., vLLM, TensorRT-LLM, SGLang); ability to diagnose and resolve performance issues at the engine level

Preferred

  • Model Landscape Awareness: Broad knowledge of state-of-the-art open-source models and strong judgment on model selection for specific customer use cases, hardware profiles, and performance targets
  • Experience: 5+ years in a technical role, with a strong focus on inference systems, open-source LLM deployment, or post-training workflows

Pay

USD 270,000 - 300,000

Every job at Together AI