Senior ML Infrastructure Engineer, Large-Scale Inference

CNA Search; United States; On-site; USD 170,000 - 230,000; Full time

Job summary

CNA Search is seeking a Senior AI/ML Research Engineer to advance large-scale AI inference, synthetic data generation, and distributed training environments. You will build scalable pipelines, optimize inference performance, and contribute to distributed systems supporting state-of-the-art models.

The role emphasizes hands-on engineering, collaboration with researchers, and publishing research at top conferences.

Qualifications

• Strong AI/ML engineering background with production systems experience.
• End-to-end AI/ML pipeline design and implementation.
• Experience with distributed inference and large-model optimization.
• Hands-on with inference frameworks such as vLLM or SGLang.

Responsibilities

• Design and build large-scale synthetic data generation pipelines and orchestration systems.
• Optimize AI inference workloads for performance, cost, memory, and compute utilization.
• Build and improve distributed inference infrastructure for large-scale AI models.
• Contribute to open-source libraries and frameworks for synthetic data generation and distributed reinforcement learning.
• Research and implement new approaches to model inference, training, and post-training.
• Collaborate with researchers and engineers working on large-scale AI systems.
• Contribute research suitable for publication at conferences such as ICML and NeurIPS.
• Translate highly technical work into clear technical content for developers and users.
• Stay current with advances in AI infrastructure, distributed inference, synthetic data, and model optimization.

Skills

AI/ML engineering

Distributed systems

Inference optimization

Research to production

Open-source collaboration

Tools

vLLM

SGLang

GPU optimization

Job description

CNA Search is seeking a Senior AI/ML Research Engineer to advance large-scale AI inference, synthetic data generation, and distributed training environments. You will build scalable pipelines, optimize inference performance, and contribute to distributed systems supporting state-of-the-art models.

The role emphasizes hands-on engineering, collaboration with researchers, and publishing research at top conferences.