Llm Serving Jobs

Our work spans efficient LLM training and inference, parallel and diffusion-based generation, sparsity, scaling laws, and training dynamics.

Dana is multi-tenant and serves critical enterprise workloads, so scale and reliability tradeoffs are part of the job.

You will serve as a key technical leader in delivering and validating all software and hardware components for Cerebras API Features.

Drive support for emerging LLM architectures and inference workloads.

Practical understanding of modern AI systems, including LLMs, AI agents, RAG architectures, model serving, prompt engineering, and agent

Practical understanding of modern AI systems, including LLMs, AI agents, RAG architectures, model serving, prompt engineering, and agent

Practical understanding of modern AI systems, including LLMs, AI agents, RAG architectures, model serving, prompt engineering, and agent

Serve as a GenAI/LLM expert across the company – owning best practices for architecture, safety, evaluation, and deployment.

This engineer will serve as a technical owner across the AI and automation lifecycle.

Any job offer made will be contingent upon the applicant’s capacity to serve in compliance with U.S. export controls.

tags, 301 redirects, open graph (OG) tags, site architecture, and schema markup, including emerging optimizations for AI/LLM search.

software products Familiarity with trade compliance, including customs, export controls, and ITAR-regulated programs Experience building LLM-powered

: Techniques to collect and select high-quality data, which can help models to train or tune more quickly or to higher quality; LLM

Strong analytical and technical skills, including advanced Excel proficiency, reporting tools, and experience leveraging AI tools (e.g., Claude, LLMs

Nice to have: Experience with Snapdragon Automotive, ARM Ethos, or specialized NPU pipelines Background in running quantized LLMs