Amazon
Nov 2021 - Present
- Led a three-engineer team shipping a Triton Python backend fronting a vLLM-served LLM: p50 of 5 to 10 ms per signal, and a concurrency refactor that took sustained throughput from about 8 to 80 requests per second on the same hardware.
- Wrote the gRPC layer that lets any pipeline of the C++ speech framework behind Nova Sonic ship as a containerized service in under 300 lines of integration code; adopted org-wide, alongside a static service registry of my design.
- Led a RAG personalization effort for speech recognition, cutting LLM round trips per request from three to two and moving retrieval off the critical path.
- Consolidated a 500k-line C++ engine’s cloud and on-device builds into one source tree across 12 toolchains, replacing fork-and-patch releases that took days to weeks.
- Authored production AWS CDK infrastructure for served models, migrated 10k+ metrics to CDK-managed CloudWatch, and built a pipeline publishing 200+ live A/B dashboards.
L3Harris Technologies
May 2017 - Nov 2021
- Took on a number of diverse internal Research and Development projects, using both Waterfall and Agile methodologies.
- Designed and developed safety-critical software as both an individual contributor, and as a de-facto project owner.
- Took initiative to develop novel internal tools to apply cutting-edge technologies to improve existing processes.
- Acted as a mentor for multiple new hires, familiarizing them with L3Harris software development process and procedure.
Wasatch Solutions
August 2013 - May 2017
- Acted as the primary systems administrator for a number of organizations, providing SaaS targeted at small businesses.
- Performed customer-specific modifications to delivered software, working in SQL, PHP and Javascript.
- Used technical writing skills to build extensive internal documentation, as well as simple, user-friendly ”how-tos”