Inference Engineer - Member of Technical Staff
Designworks Talent is hiring for Inference Engineer - Member of Technical Staff in Bellevue. Hybrid, Staff level. First seen November 11, 2026; open as of November 19, 2026. Jobs taken straight from company career pages — no aggregator in between.
Save to applyFree forever. No commitment, no card required.
- Company
- Designworks Talent
- Where
- Bellevue
- Type
- Full-time
- Arrangement
- Hybrid
- Level
- Staff
- First seen
- November 11, 2026
- Listed via
- Ashby
- Open for
- 7 days, as of November 19, 2026
About this job
This position is responsible for developing and maintaining the model-serving infrastructure that powers a next-generation AI inference platform, with emphasis on high-throughput, low-latency, and dependable inference for production-scale APIs. The role involves working on the infrastructure layer that efficiently serves large models, in collaboration with teams focused on GPU performance, AI training, platform engineering, and operations. This is a hybrid role based in Bellevue, WA, with an expectation of approximately three days per week on-site.
Schedule: Hybrid, roughly three days per week in the office
Responsibilities
- Develop and manage production-grade model-serving and inference systems for high-throughput, low-latency AI workloads
- Enhance inference infrastructure to improve token throughput, latency, scalability, and cost efficiency across various model architectures and workloads
- Architect solutions to maximize GPU utilization while ensuring consistent performance and reliability
- Advance scalability and operational robustness of inference platforms in response to growing customer demand
- Collaborate with AI training, GPU performance, orchestration, and infrastructure teams to facilitate seamless model-to-production transitions
- Implement monitoring, alerting, and operational procedures to sustain reliable inference services
- Address and resolve performance, reliability, and capacity issues across inference workloads
- Influence architectural decisions and engineering standards as the platform evolves
Requirements
- Proven experience in building and operating production machine learning inference or model-serving systems at scale
- Deep knowledge of performance trade-offs in serving large AI models, including latency, throughput, memory usage, and cost efficiency
- Experience in designing reliable distributed systems or production infrastructure
- Familiarity with GPU-backed AI workloads and the complexities of scaling inference systems
- Solid engineering fundamentals with the ability to independently manage complex technical challenges
- Ability to thrive in a fast-paced environment where systems and processes are developed from scratch
- Must have U.S. work authorization
- Open to relocating to the Bellevue, WA area if not currently local
Nice to have
- Hands-on experience with modern inference-serving frameworks such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or similar
- Experience in optimizing LLM inference workloads or large-scale AI serving platforms
- Background in operating API-based AI products or high-volume production services
- Experience with GPU scheduling, distributed systems, Kubernetes, or cloud infrastructure platforms
- Knowledge of model optimization techniques including quantization, batching, caching, or performance tuning
- Experience at a hyperscaler, AI lab, GPU cloud provider, or large-scale ML infrastructure organization
Benefits
- health, dental, and vision coverage
- 401(k) plan with employer match
- paid holidays
- merit-based raises, annual performance bonus, and long-term incentives for eligible positions
Read more and apply on Designworks Talent's site
Questions about this job
When was this Inference Engineer - Member of Technical Staff job at Designworks Talent posted?
Destava first saw it on November 11, 2026, on Designworks Talent's own careers page (Ashby).
Is Designworks Talent still accepting applications for it?
It was open on Designworks Talent's own site when Destava last read it, on November 19, 2026, 7 days after we first saw it. When the company takes it down, this page says the job has closed.
How do I apply for Inference Engineer - Member of Technical Staff at Designworks Talent?
On Designworks Talent's own site, at jobs.ashbyhq.com: open the posting. Destava does not take the application. Save the job to your Destava board to track it, see how well you fit and tailor your résumé to it.
Is this Designworks Talent job posting legit?
Destava read it on Designworks Talent's own careers page at jobs.ashbyhq.com, run on Ashby, not on a job board. First seen November 11, 2026. Apply on the company's own site, and never pay to apply for a job.
Is this job remote?
It is hybrid: part of the week on site in Bellevue, the rest from home.
What other jobs is Designworks Talent hiring for?
Designworks Talent has 23 open postings on its own site: see all jobs at Designworks Talent.
How many software developers jobs are open in Seattle?
1,800 open, 216 of them new this week, at 184 companies: see them all.
More jobs like this
MK1 Lunar Software Development Engineer III (Hardware-in-the-loop Software)
Save to applySenior Software Engineer, World Model
Save to applyStaff Software Engineer
Save to applyPrincipal Software Engineer (Platform Team)
Save to apply
See all 1,800 Software Developers jobs in Seattle
A search agent finds the jobs this list misses: the ones that mean the same without the same words. Have Destava watch for inference engineer - member of technical staff jobs in Bellevue, new matches every morning on your own account.
Applying to this one?
See how well you fit, before you apply
Save it to your board. Add your résumé once, and Destava shows where you are strong, what is missing and how to pitch yourself, then tailors your résumé to this posting.
- Found it
- Save it
- See your fit
Free forever. No commitment, no card required.
With Destava: Save to apply · Tailor my résumé · Write a cover letter
This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.