Research Engineer, Infrastructure, Inference

Thinking MachinesSan FranciscoResearch Infrastructure (ML Infrastructure and Training Stack)

Apply on company site

Opens the official Thinking Machines careers page

Salary

$350K - $475K USD

Job type

Full-time

Work mode

Remote

Posted

4 Aug 2026

Status

Open · checked 7d ago

About this role

Thinking Machines seeks a Research Engineer for Infrastructure and Inference to design and scale systems powering advanced AI models in San Francisco or remotely. This full-time position suits technical professionals eager to enhance AI infrastructure performance, latency, and reliability.

Role Overview

This position focuses on building, optimizing, and scaling the infrastructure that supports frontier artificial intelligence models. The chosen candidate will make model inference faster, more cost-effective, and reliable, allowing research teams to push model capabilities without encountering system bottlenecks. This infrastructure role ensures that evaluations, experiments, and production deployments run efficiently at scale.

Key Responsibilities

Partner with researchers and engineers to transition advanced AI models into production environments.

Collaborate with research teams to facilitate high-performance inference for unique model architectures.

Create and execute new tools, techniques, and architectures to boost efficiency, throughput, latency, and overall performance.

Fine-tune codebases and the compute fleet, including GPUs, to maximize memory, bandwidth, and hardware FLOPs.

Scale orchestration frameworks such as Kubernetes, Ray, and SLURM for distributed inference, large-batch serving, and evaluation.

Define standards for observability, reproducibility, and reliability throughout the inference stack.

Share insights via open-source libraries, technical reports, or internal documentation to contribute to the field of scalable AI infrastructure.

Requirements

Holds a bachelor degree or equivalent experience in engineering, computer science, or a related field.

Possesses an understanding of system architectures underlying deep learning frameworks like PyTorch and JAX.

Demonstrates experience utilizing inference serving systems optimized for latency and throughput, such as vLLM or SGLang.

Thrives in a collaborative setting alongside diverse cross-functional partners and domain experts.

Displays a proactive mindset with a bias for action to ship initiatives across different teams and technical stacks.

Demonstrates strong engineering abilities to write maintainable, performant code and debug complex codebases.

Nice to Have

Background in supporting or training large language models containing hundreds of billions of parameters or more.

Knowledge of hardware-aware optimizations, GPU parallelism, and distributed compute systems.

Past contributions to open-source systems infrastructure or machine learning projects like PyTorch, Triton, DeepSpeed, XLA, vLLM, or SGLang.

A proven history of boosting research productivity via infrastructure design and process enhancements.

Skills and Tools

PyTorch

Kubernetes

JAX

Ray

SLURM

vLLM

SGLang

Triton

DeepSpeed

XLA

GPUs

Salary and Benefits

Annual salary range between $350,000 and $475,000 USD, depending on background, skills, and experience.

Comprehensive medical, dental, and vision health benefits.

Unlimited paid time off (PTO).

Paid parental leave.

Relocation support provided as needed.

Visa sponsorship available for qualifying candidates.

About the Company

Thinking Machines builds artificial intelligence designed to extend human will and judgment. The organization trains frontier models using Inkling, creates Tinker for personalized model creation, and develops interfaces that improve human-AI communication.

How to Apply

Interested candidates should visit the official Thinking Machines careers page to submit an application for this opportunity.

Skills and tech stack

PyTorch Kubernetes

Questions candidates ask

What is the location for this role?

The position is based in San Francisco, California, with remote flexibility available.

What is the salary range for the Research Engineer position?

The expected annual salary range is $350,000 to $475,000 USD, determined by background, skills, and experience.

Does Thinking Machines offer visa sponsorship?

Yes, Thinking Machines sponsors visas and works through the process together with the candidate.

What benefits are provided with this job?

Benefits include generous health, dental, and vision coverage, unlimited paid time off, paid parental leave, and relocation support.

What are the core technical skills required?

Applicants need a background in deep learning frameworks like PyTorch or JAX, experience with inference serving systems such as vLLM or SGLang, and strong software engineering capabilities.

Ready to apply?

The application is on the official Thinking Machines careers page.

Apply on company site