Latest AI JobsBrowse Jobs
D

Staff Inference Engineer

designworkstalentBellevueEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Senior
Posted
2 Oct 2026
Status
Open · checked 7d ago

About this role

The Staff Inference Engineer position is a hybrid role based in downtown Bellevue, Washington, requiring approximately three days per week in the office. This opportunity suits experienced infrastructure and machine learning engineers who want to build and operate large-scale model-serving systems within a fast-moving AI environment.

Role Overview

This foundational engineering role focuses on constructing the infrastructure layer required to bring artificial intelligence models from research settings into dependable production services. The team delivers high-throughput, low-latency, and reliable inference experiences that empower customers to utilize advanced artificial intelligence capabilities through production-scale application programming interfaces. Practitioners work at the intersection of distributed systems, machine learning infrastructure, graphics processing unit computing, and large-scale production environments.

Key Responsibilities

Construct and operate production-grade model-serving and inference systems that support high-throughput, low-latency artificial intelligence workloads.
Refine inference infrastructure to maximize token throughput, latency management, scalability, and cost efficiency across varied model architectures.
Design systems that achieve high graphics processing unit utilization while preserving predictable performance and dependability.
Enhance the operational maturity and scalability of inference platforms in response to rising customer demand.
Coordinate with artificial intelligence training, graphics processing unit performance, orchestration, and infrastructure teams to facilitate smooth transitions from development to production.
Implement monitoring, alerting, and operational practices to sustain dependable inference services.
Diagnose and resolve capacity, performance, and reliability challenges across multiple inference workloads.
Shape architectural decisions and engineering standards throughout the platform evolution.

Requirements

Proven history of building and operating production machine learning inference or model-serving systems at scale.
Comprehensive knowledge of performance trade-offs associated with serving large artificial intelligence models, encompassing latency, memory utilization, throughput, and cost efficiency.
Background in designing reliable distributed systems or production infrastructure.
Familiarity with graphics processing unit-backed artificial intelligence workloads and scaling challenges.
Solid engineering fundamentals with the capacity to independently own complex technical problems.
Ability to thrive in a rapid environment where systems and processes are established from the beginning.

Nice to Have

Background utilizing modern inference-serving frameworks such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or related tools.
Experience tuning large language model inference workloads or large-scale artificial intelligence serving platforms.
History of operating application programming interface-based artificial intelligence products or high-volume production services.
Familiarity with graphics processing unit scheduling, Kubernetes, distributed systems, or cloud infrastructure platforms.
Knowledge of model optimization techniques like quantization, caching, batching, or performance tuning.
Experience operating within a hyperscaler, artificial intelligence lab, graphics processing unit cloud provider, or large-scale machine learning infrastructure organization.

Skills and Tools

vLLM
SGLang
TensorRT-LLM
Triton Inference Server
Kubernetes
Distributed systems
Graphics processing unit scheduling

Salary and Benefits

Competitive base pay tailored for the Bellevue market, alongside potential merit increases, annual bonuses, and long-term incentives based on individual performance.
Medical, dental, and vision insurance access for United States-based employees.
Four hundred one thousand retirement plan options featuring a company match.
Paid holidays provided per calendar year.

About the Company

The organization operates as a well-funded, rapidly growing artificial intelligence infrastructure company developing a cloud platform to power the complete lifecycle of artificial intelligence. Backed by long-term investments, the company merges startup agility with the stability of an established parent organization, supporting workloads that range from large-scale compute and model training to fine-tuning, inference, and emerging agentic applications.

How to Apply

Interested candidates should apply directly on the official company careers page.

Skills and tech stack

vLLMSGLangTensorRT-LLMTriton Inference ServerKubernetesLLMMachine LearningFine-tuningDistributed Systems

Questions candidates ask

Where is the job located?

The role is a hybrid position located in downtown Bellevue, Washington, requiring approximately three days per week in the office. Candidates elsewhere in the United States who are open to relocation may also apply.

Is visa sponsorship available for this position?

No, United States work authorization is required, and visa sponsorship is not currently available.

What kind of benefits are provided?

United States-based employees receive medical, dental, and vision insurance, a 401(k) plan with company match, and paid holidays per calendar year.

What technologies and frameworks are helpful for this role?

Helpful technologies include inference-serving frameworks like vLLM, SGLang, TensorRT-LLM, and Triton Inference Server, as well as Kubernetes and graphics processing unit scheduling tools.

What is the focus of the engineering team?

The team focuses on building and operating model-serving systems, optimizing inference infrastructure for low latency and high throughput, and ensuring reliability as customer usage scales.

Ready to apply?

The application is on the official designworkstalent careers page.

Apply on company site