Arkaan QuanungaRoku · AI Innovation
Software Engineer · AI Innovation & Automation @ Roku|London, UK

Engineering Autonomous QA & Multi-Agent AI Systems.

I architect production agentic platforms that replace repetitive manual testing with intelligent machine reasoning. Currently turning exploratory testing into autonomous reinforcement-learning and multi-agent workflows at Roku, backed by distributed video infrastructure, mechanical-engineering foundations, and spatial computing hardware builds.

Explore Featured SystemsDownload CV (PDF)Get in touch
Arkaan Quanunga, Software Engineer in London
Arkaan QuanungaSoftware Engineer · London
16 monthsProduction autonomous QA platform, May 2025 – present
~4,000Commits across a 17-engineer contributor base
~70%Led implementation of version-control history
7Runtime services (API, worker, UI, dual validators, scheduler, MCP)
Recognition

Patent pending and a published NVIDIA article

Patent pending · US & EU

Autonomous software verification

The Roku stack — Explorer, QANTUM, and Forge — is a patent-pending invention for turning manual QA into a data-driven process that finds functional and visual defects on devices with less manual oversight.

Read it on the career timeline
NVIDIA Developer Blog

Enabling Customizable GPU-Accelerated Video Transcoding Pipelines

Written with NVIDIA engineers at V-Nova. The article covers VC6 codec performance and a GPU-accelerated transcoding pipeline, published on NVIDIA’s developer blog.

Read the NVIDIA article
Intro

Intro

Intro
Core Engineering Deliverables

Featured Architecture Case Studies

View all systems and earlier projects
Autonomous Systems & RLMay 2025 – Present (~16 months in production)

Roku Explorer

Autonomous Exploratory Testing Platform

A production autonomous QA platform for firmware and Grand Central product areas. Combines PPO/LSTM reinforcement learning, ChromaDB multimodal RAG, dual validators, and MCP-based device control to navigate device UIs, surface potential issues, and flag visual regressions with minimal human oversight.

Multi-serviceProduction stack
RL + RAGArchitecture
MCPDevice control
PythonPyTorch (PPO / LSTM)ChromaDBFlask+6 more
Explore Architecture
Multi-Agent SystemsAug 2026 – Present

QANTUM

Slack-Native Multi-Agent QA Orchestrator

A Slack-native multi-agent QA orchestration platform routing engineering and QA requests across specialized agents via an extensible capability protocol. Features shared and user memory, Model Context Protocol (MCP) integrations, and autonomous MR/PR generation and validation flows—backed by production usage across ~100 engineers.

100Engineers
5,199Agent runs
0.17%Run failure rate
PythonClaude Agent SDKMCP ProtocolLiteLLM+4 more
Explore Architecture
AI Test Automation2026 – Present

Forge

AI Test-Authoring & Automation Agent

An intelligent AI automation agent that investigates product-area workstreams, creates detailed automation tickets, and autonomously generates, validates, and runs regression test suites across repositories using isolated git worktrees.

AutonomousWorkflow
WorktreesIsolation
Gated CIQuality
PythonGit WorktreesPytestLLM Reasoning+3 more
Explore Architecture
Augma
Spatial Computing & AR Hardware2021 – Present (Active Solo Build)

Augma

Headband-Monocle Augmented Reality Wearable

A bespoke augmented reality wearable adopting a futuristic headband-monocle form factor. Features real-time road sign and obstacle detection using YOLO26, MediaPipe wrist-displacement gesture tracking, an interactive 4-panel glass HUD, and a balanced weight distribution architecture.

MonocleForm Factor
YOLO26Vision Model
Wrist GesturesInteraction
PythonYOLO26MediaPipeOpenCV+3 more
Explore Architecture
CURRENT PRODUCTION WORK · 2025–PRESENT

Transforming Manual QA into an Autonomous, Data-Driven Pipeline

At Roku, I develop and deploy the next evolution of quality engineering: agent systems that autonomously navigate physical device interfaces, author robust regression tests, and orchestrate across complex developer tools. This unified stack connects code changes directly to risk-based automated physical device exploration.

ExplorerRL + ChromaDB RAG UI device navigation
QANTUMSlack-native multi-agent capability protocol
ForgeAI test-authoring in isolated git worktrees
Review Full Career TimelineRead Explorer Architecture
Systems & Stack Matrix

Technical Capabilities & Engineering Domains

Proven across production multi-agent systems, large-scale video transcoding cloud infrastructure, and real-time computer vision hardware.

Autonomous QA & RL

PPO and LSTM reinforcement learning policies combined with multimodal vision models and ChromaDB vector retrieval to navigate state spaces autonomously.

PPO / LSTMChromaDBVision LLMs

Multi-Agent Systems

Capability routing protocols, Model Context Protocol (MCP) integrations, isolated agent memory, and automated code review Remediator loops.

MCP ProtocolClaude SDKSlack Bolt

Distributed Cloud & Video

Scalable AWS infrastructure automated with Terraform, FFmpeg pipelines, GPU transcoding acceleration (NVIDIA DevBlog), and VMAF perceptual quality benchmarking.

AWS TerraformDocker / K8sFFmpeg / CUDA

Edge Vision & AR

Real-time object detection (YOLO26), MediaPipe hand gesture tracking, monocle optical pipelines, and spatial glass HUD compositors.

YOLO26MediaPipeEmbedded Linux

Interested in Autonomous QA or Multi-Agent Architectures?

Based in London, UK. Open to technical advisory conversations, deep-tech collaborations, and discussions on the future of autonomous software engineering.

Send EmailLinkedInGitHubYouTubeInstagram