Inference & Post-Training Engineer (FDE) for Production AI

Together Computer Inc; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Startup equity

Health insurance

Remote work flexibility

Job summary

Together AI seeks a Forward Deployed Engineer focused on inference and post-training to partner with strategic customers and production AI teams. You will optimize inference pipelines, guide LoRA/SFT/DPO/RLHF workflows, and collaborate with SAs, CX, and Sales to meet tough POC requirements and drive platform adoption.

The role emphasizes hands-on tuning, production readiness, and direct support for customers. Remote-friendly, with opportunities across multiple markets and hardware configurations.

Qualifications

• 5+ years in a technical role focusing on inference systems or post-training workflows.
• Hands-on experience with open-source LLM deployment and production pipelines.
• Deep knowledge of cache tuning, decoding, tensor and pipeline parallelism, and quantization.
• Experience with LoRA, SFT, DPO, RLHF, and GRPO in real deployments.
• Familiarity with modern open-source models and model selection for hardware targets.
• Strong Python skills and ability to operate in production environments.

Responsibilities

• Optimize inference engines and configurations for customer deployments.
• Tune caches, decoding strategies, parallelism, and quantization to meet latency targets.
• Drive hands-on RL training runs and guide customers through post-training pipelines.
• Serve as a technical contact for strategic accounts and align configurations with milestones.
• Onboard customers with correct inference and post-training settings from day one.
• Provide feedback to product teams based on field insights and adoption needs.

Skills

Inference systems

Open‑source LLM deployment

Post‑training workflows

Python programming

Production environments

Tools

vLLM

TensorRT-LLM

SGLang

Job description

Together AI seeks a Forward Deployed Engineer focused on inference and post-training to partner with strategic customers and production AI teams. You will optimize inference pipelines, guide LoRA/SFT/DPO/RLHF workflows, and collaborate with SAs, CX, and Sales to meet tough POC requirements and drive platform adoption.

The role emphasizes hands-on tuning, production readiness, and direct support for customers. Remote-friendly, with opportunities across multiple markets and hardware configurations.