Research Engineer — LLM Fine-Tuning & Model Routing

Run BiOS; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 200,000; Full time

Job summary

Run BiOS runs serverless inference across the major open model families and fine-tunes custom models on dedicated GPUs. As a Research Engineer you improve the models themselves — from bios-adaptive routing across the model pool, to the fine-tuning methods and alignment recipes customers run.

You turn research into behavior that serves production traffic, and collaborate with product engineering to make research outcomes visible and controllable in the product.

Qualifications

• At least 5 years in machine learning engineering or research, with meaningful time on large language models.
• Hands-on experience fine-tuning open-weight models: PyTorch, distributed training, parameter-efficient methods.
• Evaluation rigor: when you say a model got better, you can show how you know.
• Engineering fundamentals strong enough that someone else can reproduce your experiments.

Responsibilities

• Develop and evaluate routing strategies for bios-adaptive across the open-model pool, and measure what they do to quality, latency, and cost.
• Design fine-tuning and alignment recipes — SFT, LoRA/QLoRA, DPO-family objectives, continued pre-training — that behave predictably on dedicated-GPU infrastructure.
• Build evaluation harnesses that catch regressions before customers do.
• Read the literature, reproduce what matters, discard what does not, and ship what wins.
• Work with product engineering to make research outcomes visible and controllable in the product.
• Write down what you learn — internal notes, docs, and occasionally public posts.

Skills

ML engineering

Large language models

PyTorch

Distributed training

Parameter-efficient methods

Reproducible research

Job description

Run BiOS runs serverless inference across the major open model families and fine-tunes custom models on dedicated GPUs. As a Research Engineer you improve the models themselves — from bios-adaptive routing across the model pool, to the fine-tuning methods and alignment recipes customers run.

You turn research into behavior that serves production traffic, and collaborate with product engineering to make research outcomes visible and controllable in the product.