Inference Researcher (AI)

Location

Location: Must be able to work in-person in New York or San Francisco offices

Company

hirify.global is an AI infrastructure startup building a platform for the full lifecycle of large language models, including training, deployment, and inference, serving category-defining customers and backed by a $4.65B valuation.

What you will do

• Own end-to-end inference research projects such as speculative decoding, quantization (FP8, INT4), KV-cache and memory management, and autoscaling for serverless traffic.
• Train custom speculators on real production traffic and evaluate improvements using acceptance length metrics.
• Collaborate directly with customers and Forward Deployed Engineers to deploy and tune models.
• Maintain and expand collaborations with external research labs on advanced inference techniques.
• Work with engineering teams to convert research innovations into production serving products and primitives.
• Help shape the research agenda by independently driving research bets from idea to result.

Requirements

• Ability to work onsite in New York or San Francisco
• Research or systems background in LLM inference with demonstrable work.
• Fluency in LLM serving stack components including kernels, quantization, schedulers, and autoscaling.
• Proven track record of shipping research or systems used by others in lab or industry.
• Self-driven to take research projects from concept to outcome in an open team environment.