Senior AI Infrastructure Engineer – High-Performance Serving

Data Direct Networks; California (MO); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Vacation plans

Paid holidays

Bonus programs

Tuition reimbursement

Employee referral program

Excellent medical, dental and vision

Paid leave programs

Anniversary and recognition awards

Job summary

Data Direct Networks is seeking an engineer to build and optimize LLM serving and inference systems for production environments. You will work on performance across GPU and CPU pathways and tackle bottlenecks in memory, storage, and throughput.

You will design and scale systems to support RAG and retrieval-heavy AI workloads, contributing to infrastructure where storage architecture and system efficiency directly affect AI performance.

Qualifications

• Experience building production AI systems and serving workloads.
• Understanding of compute/memory/storage interactions on inference.
• Hands-on work near the systems layer with GPU/CPU tuning.
• Ownership across model serving, retrieval, caching, or distributed performance.

Responsibilities

• Build and optimize LLM serving/inference systems for production.
• Improve performance across GPU and CPU pathways.
• Scale systems for RAG and retrieval-heavy workloads.
• Address bottlenecks in memory, storage, and throughput.

Skills

AI systems

Model serving

Inference performance

System optimization

Distributed systems

Job description

Data Direct Networks is seeking an engineer to build and optimize LLM serving and inference systems for production environments. You will work on performance across GPU and CPU pathways and tackle bottlenecks in memory, storage, and throughput.

You will design and scale systems to support RAG and retrieval-heavy AI workloads, contributing to infrastructure where storage architecture and system efficiency directly affect AI performance.