Meta · Menlo Park, CA
RPC Infrastructure & Distributed Systems
- Led a high-impact 0-to-1 strategic effort to design and build a standardized
gRPC framework layer directly integrated with Meta's massive legacy Thrift
infrastructure, enabling modern multi-language interoperability across core
microservices.
- Architected and optimized core components of ServiceRouter, Meta's global
routing and load-balancing tier, driving measurable reductions in tail latency
(P99.9) and fleet-wide CPU utilization through efficient connection
multiplexing.
- Engineered local, AI-native sidecar agents for intelligent load-shedding and
automated microservice diagnostics, leveraging local LLM inference and
Retrieval-Augmented Generation (RAG) to dynamically predict and mitigate
cascading service failures.
- Mentored senior engineers and cross-functional teams on advanced C++ concurrency
patterns, asynchronous execution models (Folly/Async), and zero-copy transport
mechanisms.
Google · Mountain View, CA
Cloud Infrastructure / Core Systems
- Designed and maintained high-throughput, low-latency RPC primitives and
asynchronous communication patterns supporting core Google Cloud and Vertex AI
infrastructure.
- Collaborated on large-scale compute fleet optimization initiatives, identifying
and resolving systemic bottlenecks in memory allocation, serialization overhead,
and thread contention.
- Pioneered high-performance data paths utilizing advanced networking primitives
(e.g., RDMA-like abstractions, user-space networking) to drastically improve
throughput for distributed machine learning training and inference workloads.
iT&X Data LLC · Blacksburg, VA
- Bootstrapped and scaled a specialized data infrastructure consultancy, designing
custom high-performance data pipelines and distributed storage engines for
enterprise clients.
- Architected lock-free concurrent execution engines in C++ and Rust, achieving
orders-of-magnitude performance improvements over traditional thread-pool
architectures for real-time data ingestion.