About Positron AI Positron AI is building next-generation AI inference accelerators designed from the ground up for low-latency, high-throughput large language model inference. Our first-generation ASIC, Asimov, is a…
Senior SRE on Nebius Token Factory, owning reliability, performance, and observability for a GPU-accelerated AI inference platform running tens of thousands of GPUs. Core stack: Kubernetes, Prometheus, Grafana, Terraform, Python/Bash, with GPU serving tools (vLLM, Triton, Ray).
Advises business units and IT teams on AI use cases, designs and develops AI automations and integrations, and ensures secure, cost-effective, sustainable AI usage across existing platforms.
Lead AI engineer architecting generative-AI workflows for cloud-infrastructure automation (Terraform, Rego, CI/CD, RAG, LLM APIs) while owning the AI enablement technical strategy and leading a distributed engineering team.