AI Engineer

Principal SW Engineer - LLM Serving (Cloud AI) | San Diego, California | On-site | $200,800 - $301,200

We're working with a global leader in semiconductor innovation and wireless technology on this exciting opportunity. Join a powerhouse engineering team dedicated to revolutionizing Cloud AI through high-performance LLM inference acceleration and next-generation silicon software.

As a Principal Engineer, you will lead the architecture and deployment of large-scale commercial software solutions. You’ll dive deep into LLM serving frameworks like vLLM and PyTorch to optimize carrier-grade machine learning workloads on multi-core SoC architectures. This is a high-impact role driving the future of AI infrastructure from R&D to global commercial deployment.

The Role

• Lead the design and development of high-performance software for LLM serving, utilizing frameworks like vLLM to maximize inference throughput.

• Architect and optimize neural networks across the full product lifecycle, focusing on Multi-modal and reasoning models for cloud-scale AI environments.

• Perform deep-dive bottleneck analysis and performance modeling on multicore architectures, including NoCs, caches, memory subsystems, and PCIe interfaces.

• Collaborate cross-functionally to bridge the gap between AI compiler technology and hardware acceleration, ensuring seamless integration with machine learning accelerators.

• Write and maintain high-performance, low-latency code in C++ and Python for sophisticated SoC architectures and math libraries.

What You'll Need

• 8+ years of professional software or systems engineering experience (or 6+ years with a PhD) in high-performance computing environments.

• Proven expertise in LLM serving frameworks (vLLM) and strong development skills in PyTorch for optimizing neural networks.

• Advanced proficiency in C++, Python, and Linux systems programming, with a focus on multicore architecture fundamentals (Memory, Bus, SoC).

• Deep understanding of linear algebra, math libraries, and neural network operators essential for machine learning acceleration.

• Master's or PhD in Computer Science or Computer Engineering with a track record of delivering complex commercial software projects at scale.

What's On Offer

• Competitive base salary of $200,800 - $301,200 plus a significant discretionary annual bonus program.

• Generous annual RSU grants, providing true ownership in a global tech pioneer.

• Comprehensive benefits package designed to support health, wealth, and work-life balance.

• Opportunity to work at the forefront of the AI revolution, influencing how the world’s largest models are served and scaled.

Apply via Haystack today!