Founding Inference Research Engineer

Find and remove bottlenecks across model representation, GPU kernels, runtimes, and serving for open-weight models.

About Gradiated

Gradiated is a research lab focused on inference. We co-design software and hardware for efficiently serving open-weight models.
Our goal is to maximize intelligence per joule. We work across model behavior, software, systems, and silicon to find better ways to run models.
We start by thinking about the model as a mathematical function, and map that out onto hardware and then build software on top of that which is custom to each model. This maximises performance and removes wasted abstractions.
We are early. You will help set the technical direction and the way the company works.

We are building an inference research team to find where current hardware and software waste time, memory, and energy when serving open-weight models.
You will measure those bottlenecks, test changes across the inference stack, and turn useful results into production systems. Your findings will also inform our silicon work.

Measure target models and workloads on current NVIDIA and AMD hardware.
Design and implement kernels, numerical formats, memory layouts, and cache policies.
Change runtimes, schedulers, distributed execution, and serving paths when they limit the system.
Test latency, throughput, energy use, model quality, correctness, and reliability on real workloads.
Turn research results into production services.
Share research publicly so that others can learn about how inference research is done.
Work with the silicon team to identify hardware bottlenecks and design opportunities.

Kernels and fused execution paths for exact model shapes.
Low-bit formats that preserve model quality.
KV-cache layout, movement, compression, and reuse.
Sparse and mixture-of-experts execution.
Speculative and parallel decoding.
Prefill and decode scheduling across multiple GPUs.
Performance models that explain the gap between hardware limits and measured results.
Runtime designs for long-running agent workloads.

You have built an ML systems, compiler, runtime, or kernel project, and you can explain your decisions and results in detail.
You can work in Python and a systems language such as C++ or Rust. We use C++ mostly.
You can write CUDA or HIP kernels, or you have strong low-level systems experience and can learn GPU programming.
You understand transformer execution, including attention, memory movement, and numerical precision.
You use profiling and controlled experiments to identify system limits.
You are open to learning about hardware, and what is limiting the execution of the model.
You can maintain production code, not only experimental code.
You can explain hard technical solutions clearly

You want to work within one layer of the inference stack.
You want framework integration to be the main technical work.
You want papers or notebook results to be the primary output.
You aren't excited by rewriting things from scratch, and taking time to find the globally optimal solution to a problem.
You need a complete specification before you can investigate a problem.

We like to experiment a lot and do the hard thing even if it's likely to fail.
We work in the office on Monday, Wednesday, Friday. We value working in person to solve hard problems, but are also flexible, some of the team work abroad for short periods.

We offer top-of-market compensation, with significant equity.
We pay at the top of the market because talent density is what allows us to build the most efficient inference. We want a small team of exceptional people who have fun solving hard problems together.

A 60-minute call about your goals and the role.
We get together in person and talk through the problems we will work on.
A paid in-person working session, so we can get to know you and you can meet the team.
References and an offer decision.

Apply

If this sounds interesting to you, we'd like to hear from you. Fill in the form below and we'll get back to you within a few days.

Loading the application form