Clera - Your AI talent agent
Login
Start
Clera - Your AI talent agent

Your AI-talent agent.
Connecting talents with dream jobs.

Follow us on LinkedInRefer & Earn

Tools

Resume CreatorCareer CoachSalary CalculatorResume Review

Explore

JobsCompaniesAcquihire

Company

About UsCareersFAQsBlog

Legal

TermsPrivacyBug Bounty
Back to Companies
IInference logo

Inference

The AI compute ecosystem for future leaders: Inference.ai enables flexible allocation of virtualized GPUs to different tasks and containerized workflows.

11-50 employees
San Francisco
1 Job

Open positions

Apply

Senior Software Engineer - Model Performance

<p style="min-height:1

$220k - $320k
San Francisco

The AI compute ecosystem for future leaders: Inference.ai enables flexible allocation of virtualized GPUs to different tasks and containerized workflows.

Tech Stack

ML SystemsInference OptimizationGPU ProgrammingPythonC++LLM Inference FrameworksGPU ArchitectureCUDAQuantizationSpeculative DecodingContinuous BatchingKV Cache ManagementPyTorchPerformance Improvement

Frequently Asked Questions

What does Inference do?

The AI compute ecosystem for future leaders: Inference.ai enables flexible allocation of virtualized GPUs to different tasks and containerized workflows.

How many employees does Inference have?

Inference has 11-50 employees employees.

What industry is Inference in?

Inference operates in the IT Services and IT Consulting industry.

How many open jobs does Inference have?

Inference currently has 1 open position on Clera.

Where is Inference based?

Inference has offices in San Francisco, United States. They offer on-site positions for their team members.

Why should I join Inference?

Inference is a leading IT Services and IT Consulting company offering exciting career opportunities. With 1 open positions, now is a great time to join their growing team.

Is Inference hiring remotely?

Inference has 1 open positions. Work arrangement details vary by role - view individual job listings for specific information about remote work options.