Skip to main content
Brian WongBW
Open to opportunities

Brian Wong

@brianwong4

Senior Full-Stack AI engineer building AI-native conversational search and meeting intelligence end-to-end.

United States
Message

What I'm looking for

I’m looking to build AI-native, product-driven systems end-to-end—RAG + LLM orchestration, high-performance APIs, and real-time UIs—where I can scale reliability and improve relevance/latency with measurable impact.

I’m a Senior Full-Stack AI Engineer who builds product-driven, AI-native systems end-to-end—turning RAG pipelines and LLM orchestration into high-performance backend APIs and real-time web interfaces. I’ve scaled conversational AI and collaboration products, focusing on measurable gains in relevance, latency, and user success.

At Perplexity, I led an AI-powered conversational search platform (Copilot-style), improving multi-turn research success by 22% (45% → 55%), answer helpfulness by 18% (28% → 33%), and reducing median latency by 25% (520ms → 390ms) while scaling to 1K+ RPS. At Otter.ai, I drove real-time meeting assistant capabilities, including transcript search and live summary pipelines—reducing search time-to-first-result by 48%, summary generation latency by 40%, and time-to-capture action items by 35% at 15K+ concurrent sessions, and I mentored engineers to accelerate independent delivery.

Experience

Work history, roles, and key accomplishments

Perplexity logoPE
Current

Full-Stack AI Engineer

Sep 2023 - Present (2 years 9 months)

Led end-to-end development of an AI-powered conversational search platform, integrating RAG workflows and LLM orchestration to deliver source-grounded answers at 1K+ RPS. Improved multi-turn research success by 22%, answer helpfulness by 18%, reduced median latency by 25%, and decreased time-to-first-token by 35%.

Otter.ai logoOT

Senior Software Engineer

Nov 2019 - Aug 2023 (3 years 9 months)

Drove development of Otter’s real-time meeting assistant, enabling live transcription, collaborative editing, semantic search, and automated summaries for 15K+ concurrent sessions. Reduced p95 orchestration API latency by 32%, cut time-to-first-result by 48%, decreased time-to-capture action items by 35%, and improved summary pipeline performance by 40%.

Google logoGO

Software Engineer

Aug 2017 - Oct 2019 (2 years 2 months)

Enhanced Google Cloud Monitoring dashboards by building high-performance UI components and backend aggregation services for real-time metric exploration. Reduced time-to-interactive by ~25% (est.), implemented gRPC + Protobuf aggregation over Cloud Bigtable, and improved automated test coverage by ~50–100 cases (est.).

Education

Degrees, certifications, and relevant coursework

University of California, Los Angeles logoUA

University of California, Los Angeles

Bachelor of Science (B.S.), Computer Science

2013 - 2017

Earned a Bachelor of Science in Computer Science at UCLA from 2013 to 2017.

Find your dream job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan