Developer Relations Engineer (AI Inference)

Location: San Francisco, California; remote work may be considered within the US for exceptional candidates

Annual salary: $200,000–$400,000 USD plus equity

Company

hirify.global was founded by the creators and core maintainers of vLLM to make AI inference cheaper and faster and grow vLLM as a leading AI inference engine.

What you will do

• Write technical deep dives, tutorials, documentation, examples, and architecture explainers for AI inference practitioners.
• Build demos, benchmarks, runnable repositories, hands-on labs, and other public technical artifacts.
• Teach concepts including KV cache, PagedAttention, continuous batching, prefix caching, prefill and decode scheduling, quantization, and speculative decoding.
• Explain GPU serving, distributed runtimes, tensor and data parallelism, and latency-versus-throughput tradeoffs.
• Host workshops and technical talks and help developers move from concepts to working code.
• Contribute to developer-facing open-source education and shape adoption of vLLM across the AI infrastructure community.

Requirements

• Bachelor’s degree or equivalent experience in computer science, engineering, machine learning, systems, or a related field.
• Strong technical understanding of LLM inference systems, model serving, GPU inference, distributed runtimes, scheduling, batching, quantization, or related infrastructure.
• Experience with vLLM or adjacent technologies such as SGLang, TensorRT-LLM, TGI, LoRAX, Ray Serve, FlashInfer, BentoML, or similar systems.
• A strong public portfolio of technical artifacts, including blogs, tutorials, workshops, courses, open-source documentation, benchmark posts, conference talks, demos, or runnable repositories.
• Ability to clearly explain complex systems concepts and create practical developer education without relying on generic content marketing.
• Strong engineering judgment, product taste, and ability to turn raw technical material into useful learning resources.

Nice to have

• Experience in ML systems, distributed systems, HPC, compilers, GPU kernels, serving infrastructure, MLOps, developer tooling, or open-source infrastructure.
• Contributions to developer-facing open source through documentation, tutorials, examples, cookbooks, demos, or community support.
• Community credibility in AI infrastructure, CUDA/GPU, Ray, vLLM, PyTorch, Modal, BentoML, Baseten, or related ecosystems.
• Widely shared technical writing, courses, architecture deep dives, demos, benchmarks, or repositories focused on LLM inference and model serving.

Culture & Benefits

• Research and Engineering environment focused on AI inference systems.
• Visa sponsorship is available on a case-by-case basis.
• Health, dental, and vision benefits.
• 401(k) company match.
• Equity included in the compensation package.