Staff Research Engineer, LLM Inference & Systems

modal; New York (NY); On-site; USD 180,000 - 240,000; Full time

Job summary

Modal is building a comprehensive LLM serving platform with a focus on end-to-end inference research. You will work with the research lead to pick high‑impact bets and own them from idea to result, shaping how we serve models at scale.

You will collaborate with customers and Forward Deployed Engineers to deploy and tune models, and you will push frontier techniques into product concepts, improving cost per token and tail latency for real workloads.

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.

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 for models that keep training after deployment, observability for quality and latency in production, or even a next-generation inference engine.
• Help shape the research agenda. None of the above is prescriptive; your work will help guide our future.

Skills

Inference research

LLM serving stack

Quantization

Autoscaling

Research bets

Job description

Modal is building a comprehensive LLM serving platform with a focus on end-to-end inference research. You will work with the research lead to pick high‑impact bets and own them from idea to result, shaping how we serve models at scale.

You will collaborate with customers and Forward Deployed Engineers to deploy and tune models, and you will push frontier techniques into product concepts, improving cost per token and tail latency for real workloads.