Member of Technical Staff, Inference & Serving (AI)

Location: Bay Area, United States; in-office

Salary: $200,000–$350,000 annual base salary, plus equity and benefits

Company

hirify.global develops diffusion-based large language models, including Mercury, for faster and more efficient AI inference.

What you will do

• Build and optimize high-performance model serving systems for low-latency diffusion LLM inference.
• Extend Kubernetes, Ray, and SLURM orchestration for distributed inference, evaluation, and large-batch serving.
• Implement load balancing, autoscaling, traffic routing, model versioning, canary deployments, and zero-downtime rollouts.
• Develop monitoring, alerting, and observability tooling to support SLAs and incident response.
• Collaborate with ML researchers to productionize new architectures, quantization techniques, and batching strategies.

Requirements

• BS, MS, PhD, or equivalent experience in Computer Science, Engineering, or a related field.
• Knowledge of SGLang, vLLM, Triton Inference Server, or TensorRT-LLM.
• Systems-level understanding of PyTorch and TensorFlow.
• Familiarity with high-performance computing and GPU programming, including CUDA.
• Experience with Docker, Kubernetes, CI/CD pipelines, and ML systems performance optimization and profiling.

Nice to have

• Experience serving large-scale language models with tens of billions of parameters or more.
• Distributed systems and cloud experience with AWS, GCP, or Azure.
• Experience with Kubeflow, Airflow, quantization, distillation, speculative decoding, continuous batching, checkpointing, or resource scheduling.

Culture & Benefits

• Work with AI researchers and engineers who pioneered diffusion models and related technologies.
• Competitive salary, equity, flexible vacation, and paid time off.
• Health, dental, and vision insurance, plus a 401(k) match.
• Catered breakfast, lunch, and dinner, with commuter subsidies.
• Collaborative and inclusive culture.