dbinfer

LLM Inference Engine. C++23, Metal, NEON

github.com/druhinb/dbinfer

• Built an Apple Silicon LLM inference engine from scratch in C++23, writing bespoke CPU (NEON) and GPU (Metal) kernels.
• Achieved 147 tok/s (Q8_0, M3 Max) GPU decode speed via successive optimization passes, 60% of llama.cpp's Metal backend.
• Designed a custom compression format for model tensors, saving 15% space vs. GGUF with a 10% decode-time increase.

drubuntu

ARMv8 Multikernel OS. C, ARMv8

github.com/druhinb/drubuntu

• Built the memory system from bare metal: a buddy allocator managing RAM in 4KB pages and a four-level page-table walker.
• Implemented same-core and cross-core message passing between processes, including UMP, a lock-free shared-memory channel.
• Wrote the ELF program loader, per-process address spaces, and multicore bring-up to run user processes across all 4 cores.

Roblox

Software Engineer Intern. June 2026 - Present. San Mateo, CA

• Shipped server logs and post-mortem server history to the creator dashboard; 60% of top 500 creators adopted them within a month.
• Built Flink pipelines processing and ingesting a combined 2M events/sec of client and server logs into sharded ClickHouse.
• Owned the read path, designing an Elasticsearch cluster to serve server details in under 200ms and logs in under 500ms at p99.
• Led container connectivity, compute scheduling, and queue trigger design for Roblox's from-scratch Lambda-style platform.
• Built Lambda worker in Rust & C; gVisor isolation, custom Luau runtime, SPIFFE mTLS, sub-100ms in-game invocations.
• Halved payload sizes and root-caused duplicate delivery in Cross-Server Messaging, Roblox's C++ inter-server bus.
• Won signoffs and SVP approval for designs and capacity estimates across 8+ partner teams, from engine security to infrastructure.

Paul G. Allen School of Computer Science & Engineering

Undergraduate Teaching Assistant. Jan 2026 - June 2026. Seattle, WA

• Taught Operating Systems to 150+ students, debugging kernels, hosting recitation for 40+ students, and managing logistics.

DropzoneAI

Research & Development Intern. Sept 2025 - Dec 2025. Seattle, WA

• Designed the agent's memory on Postgres and pgvector, carrying context across alerts to cut median investigation time 35%.
• Shipped Azure, Jira, and CrowdStrike integrations, lifting alerts resolved without analyst input from 70% to 90%.
• Built adapters normalizing alerts, tickets, and EDR telemetry into a unified evidence model the agent reasons over.

Amazon Web Services

Software Development Engineer Intern. June 2025 - Sept 2025. Seattle, WA

• Built new shard-failover pipeline for Kinesis Data Streams (Tier-0, 99.99% SLA), retiring a recurring class of long-tail outages.
• Modeled hardware telemetry in a Java/Rust service to proactively migrate at-risk shards, cutting heat-related disruptions 24%.
• Designed real-time host-failure detection over fleet telemetry, triggering shard failover before customer latency degraded.
• Drove the rollout from canaried telemetry streams to every us-west-2 host across heat, storage, and control-plane owners.

DevMatch

Software Engineer Intern. Oct 2024 - June 2025. Seattle, WA

• Built a browser IDE on AKS with Docker-in-Docker sidecars and per-tenant isolation, sandboxing 20,000+ untrusted code runs.
• Stood up an OpenTelemetry, Prometheus, and Grafana observability stack with alerting across the platform.