Teams at Parasail

Optimize and integrate LLMs across the stack from GPU kernels to Kubernetes deployments. Improve inference performance via kernel development, algorithmic techniques (quantization, speculative decoding), and contributions to open-source LLM engines like vLLM. Drive hardware utilization, profiling, and enterprise-grade scalable implementations.

Build pipeline and run full sales cycles for an early-stage AI infrastructure startup: prospecting, technical demos, POCs, negotiation, onboarding, and shaping GTM playbooks while partnering with founders and engineering.

Design, build, and secure scalable distributed backend systems for AI workloads. Implement microservice-based architectures, manage Kubernetes-based deployments, apply IaC and DevOps practices, and collaborate with performance and solutions engineering to optimize model deployment and infrastructure cost, security, and scalability.