All projects
FlowState AI2025 — Present

Enterprise Video Intelligence & Agentic Search

Backend and core platform for ingesting, understanding, and searching tens of thousands of hours of enterprise video.

Founding Engineer (Employee #1)

Video indexed
10,000+ hrs
Role
Eng #1
Stage
Early enterprise
PythonFastAPIgRPCMilvusVideo AITemporalKubernetes

As the founding engineer at FlowState AI, I'm building the platform that turns raw enterprise video into something searchable and actionable — from the ground up.

Problem

Organizations sit on enormous archives of video — recordings, operations footage, inspections — that are effectively un-searchable. Long-form video is expensive to process, hard to index, and harder still to query in the way people actually think ("find the moment where…").

The deeper problem is that video is not just another file type. It is temporal, multimodal, and evidence-heavy. A useful system needs to know what happened, when it happened, why a moment was retrieved, and where a human can verify it.

Enterprise video intelligence

Turning video archives into searchable organizational memory

Click through the product story from passive video archives to searchable knowledge, evidence-backed investigation, and decisions grounded in the original footage.

archiveorganizediscoverinvestigateevidence10,000+ hoursenterprise footageOrganizesearchable footageDiscoverrelevant contexteventspeopleactionsplacesnatural-language searchEvidencesource contextinspectverifyranked momentsActionWorkflows00:14:22Restricted zone01:03:09Dock activity02:41:36Anomaly reviewAsk natural-language questions across long-form videoReview cited evidence, timestamps, and source context
Raw video to enterprise intelligence
Natural-language searchEvidence-backed answersEnterprise analytics

Search

Find relevant moments across long-form video

Investigation

Ground answers in timestamps and source evidence

Operations

Support monitoring, analytics, and enterprise workflows

Approach

I designed and built the backend and core platform for turning long-form enterprise video into searchable organizational memory. That means scalable systems for bringing large volumes of footage into the platform, organizing it into useful context, and powering product workflows for search, investigation, monitoring, and analytics.

The work sits at the boundary between ML systems and product infrastructure: long-form video understanding, natural-language search, evidence-backed answers, real-time processing, anomaly detection, enterprise analytics, and the backend services that make those capabilities reliable enough for real deployments.

What I Built

As employee #1, my role spans architecture, implementation, and early product execution. I work across the platform layer that handles enterprise-scale video, the product systems that surface relevant moments, and the workflows that turn natural-language questions into grounded answers with inspectable evidence.

Impact

The platform powers early enterprise deployments across 10,000+ hours of video content. The goal is to make video feel less like passive storage and more like an active interface: something teams can search, investigate, monitor, and reason over at scale.

Beyond the code, I lead engineering across architecture, product, and early team building as the company's first engineer.

Note: kept intentionally high-level. Specifics are omitted for confidentiality.