Principal ML Solutions Architect - Token Factory

What you'll do

• Own complex customer engagements from architecture through production, optimizing performance, reliability, quality, and cost.
• Lead LLM inference optimization and supervised and reinforcement fine-tuning; develop reusable practices and guide customers from PoC to production.
• Partner with product, engineering, and research on customer needs and roadmap; mentor Solutions Architects and represent Token Factory externally.

What they ask for

• 8+ years of experience in ML/AI systems, including at least 4 years focused on LLMs and generative AI.
• Demonstrated technical leadership and expert knowledge of the LLM ecosystem, including model architectures, fine-tuning, and inference internals.
• Hands-on experience running LLMs in production at scale, fine-tuning and evaluation, and inference frameworks such as vLLM, SGLang, or TensorRT-LLM.
• Strong Python programming and excellent communication skills.

Nice to have

• Contributions to major OSS inference/ML projects; published research, conference talks, or technical writing in the LLM/serving space.
• Multimodal AI experience, DevOps and infrastructure-as-code proficiency, or experience building ML workflow tooling at scale.

Pay

$208,000 — $261,000 USD base salary

Tools

Python, vLLM, TensorRT-LLM, SGLang, Transformers, OpenAI/Anthropic SDKs, Kubernetes (K8s), Docker

AI focus

Production LLM inference and fine-tuning, including inference optimization, supervised and reinforcement fine-tuning, evaluation, prompt engineering, and RAG.