Summary
Andrey Krisanov is a Staff Software Engineer and Architect specializing in GenAI platforms, agent orchestration, and production LLM serving with 15+ years of experience across backend systems, SaaS, and cloud infrastructure. He architects GPU-backed, multi-model inference platforms and controlled agent/tool execution environments, having built Kubernetes-based vLLM serving on NVIDIA H200/H100/A100 and implemented semantic routing, rate-limiting, and observability for enterprise deployments. A hands-on technical leader, he combines deep reliability engineering—tuning long-context model latency and establishing Prometheus/Grafana pipelines—with cross-team governance for secure AI adoption in regulated environments. Previously a CTO and engineering lead, he has driven platform modernizations that achieved near five-nines uptime, major performance gains, and scaled engineering organizations. He brings practical experience migrating legacy systems to cloud-native architectures, introducing infrastructure-as-code and reproducible delivery, while still contributing to applied AI, RAG, and LLM systems work. Based in Moscow, he’s a pragmatic problem-solver who pairs low-level serving optimizations with product-aware architectural decisions.
11 years of coding experience
8 years of employment as a software developer
Master's degree Applied Mathematics and Information Science, Master's degree Applied Mathematics and Information Science at Bryansk State University
English, Russian