← All roles

Member of Technical Staff - Research, Inference

Modal· Engineering
Apply on company site
New York, San Francisco$150k - $350kFull-timePosted 3mo ago

About the role

Research-focused role at Modal working on end-to-end LLM inference, serving, and frontier techniques to reduce cost per token and tail latency, with opportunities to collaborate with customers and external labs.

Responsibilities

  • Own end-to-end inference research bets: speculative decoding, disaggregated prefill/decode, quantization (FP8, INT4), KV-cache and memory management, autoscaling for spiky serverless traffic, and whatever else the research agenda calls for.
  • Train custom speculators against real production traffic and feed what you learn back into target models -- acceptance length is the metric that decides the win.
  • Work directly with customers alongside our Forward Deployed Engineers to deploy and tune models, and bring what you learn back into the research.
  • Carry and expand collaborations with outside research labs, for example: - our work with ZLab on DFlash, a speculator design built on KV injection and blockwise parallel drafting - our work with SGLang on specdec and multimodal inference performance - our work on Flash Attention 4 kernels
  • Work with engineering to turn frontier serving techniques into products: primitives for disaggregation, fast weight refresh, observability for quality and latency, or a next-generation inference engine.
  • Help shape the research agenda and guide future direction.

Qualifications

  • A research-leaning or systems background in LLM inference, with work you can point to.
  • Fluency in the LLM serving stack, from kernels and quantization up to schedulers and autoscaling.
  • A record of shipping research or systems that other people build on, whether in a lab or in industry.
  • The drive to independently take a research bet from idea to result, working in the open with the rest of the team.
  • Ability to work in-person, in our NYC or San Francisco office.

Skills

Required:LLM inference experienceLMS serving stack fluencyResearch-to-production shippingIndependent research executionCollaboration with customers and field engineers
Last updated Oct 21, 2026. Interested? Apply on the company site.
Modal logo

About Modal

High-performance AI infrastructure

Bring your own code, and run CPU, GPU, and data-intensive compute at scale. The serverless platform for AI and data teams.

AI infrastructureBatchGPU scalingInferenceML workloadNotebooksObservabilityPlatform
Company profileWebsite

More open roles at Modal