Member of Technical Staff - Infrastructure & LLMs

Company: Skysight is an AI-infrastructure company based in San Francisco, CA, building large-scale batch inference infrastructure and tooling with a great user developer experience. Their mission is to build tools that increase human leverage.

Role: We are seeking an infrastructure and LLM-focused engineer to join a small, mighty team working at the forefront of large-scale inference technologies. You’ll be directly responsible for designing, owning, and improving systems designed to expand the scope of what is possible with data.

Responsibilities:
*   Scaling a secure and fault-tolerant inference system to handle many billions, or trillions of tokens in a single workload.
*   Building a high-performance data caching and lookup system.
*   Researching novel distillation techniques around a heterogenous set of use-cases.
*   Writing performance profilers, job schedulers, cost attribution models, and other scientifically-oriented code.

Ideal Candidate Fit:
*   Very technically curious, interested or experienced in distributed systems and open-source LLM technologies (professional, academic, or personal).
*   Learns fast and takes ownership.
*   Thinks from first principles, and questions default “expert” opinions.
*   Wants to ship important, well-crafted products, and have a bias towards building.
*   A kind, honest, and positive-sum person ready to have fun and learn a ton along the way.

Other: We will not be able to accommodate visa sponsorship at this time. For extra priority when applying via email, please include [HN] in the subject line.