THE OPPORTUNITY
A role worth
a closer look.
Develop and operate the inference platform used to serve language, vision and embedding models across a trading firm. Own model onboarding, GPU performance and deployment reliability. Tune scheduling, caching and distributed serving while measuring whether optimization changes preserve model quality under real production workloads.
Experience highlighted by the employer
- Hands-on NVIDIA GPU model serving and deep expertise in an inference runtime such as vLLM, TensorRT-LLM or SGLang.
- Strong Linux fundamentals, production deployment experience and the ability to profile distributed inference performance.
Location & eligibility
The employer lists Chicago. A remote or hybrid arrangement and sponsorship policy are not specified in the reviewed role description; confirm both before applying.
Compensation
USD $200,000–$250,000 / year. Employer-published annual base salary range; an annual discretionary bonus is separate.
Before you apply
This is TaskBull’s concise summary, not the employer’s full job description. Review the complete responsibilities, terms, accessibility information and privacy notice on the original application page.
Read the full employer listing ↗