01 / Executive Summary

Architected and engineered an end-to-end autonomous HR interview and assessment system inside WordPress. Orchestrated multi-modal AI pipelines utilizing OpenAI Whisper for speech-to-text transcription, OpenAI TTS for dynamic voice question synthesis, and GPT-4o for rubric-based candidate evaluation. Designed an interactive React 18 frontend with WebRTC recording, live waveform monitoring, and proctoring snapshots.

02 / The Challenge

Enterprise hiring teams face bottlenecked recruitment pipelines: screening hundreds of candidate interviews consumes hundreds of manual engineering hours, produces inconsistent subjective evaluations, and introduces high scheduling latency. Off-the-shelf SaaS alternatives are rigid, cost-prohibitive, and lack explainable multi-parameter scoring rubrics for verbal, vocal, and non-verbal candidate performance.

03 / Implementation & Solution

Engineered a standalone WordPress plugin with custom database schemas, tokenized candidate invitations, and a dual-build React 18 application (Candidate SPA & Super Admin Portal). Implemented an asynchronous background evaluation engine with status polling to prevent gateway timeouts during heavy LLM execution. Built an integrated site-wide token credit calculation subsystem with automated CSV exports.

04 / Architecture & Strategy

Decoupled WordPress & React Architecture: WordPress REST API (`/wp-json/his/v1/`) powering a modular React 18 frontend (Webpack 5, CSS Modules). Backend orchestrates OpenAI Whisper audio ingestion, TTS generation, GPT evaluation prompts, and relational tracking across sessions, invitations, and audio/video artifacts.

05 / Diagnostics & Challenges

Handling synchronous timeout thresholds on HTTP requests when transcribing long multi-question candidate audio answers and computing multi-metric AI scoring rubrics. Resolved via asynchronous job dispatching, status polling, and optimistic UI transitions. Mitigated client-side WebRTC audio capture inconsistencies across mobile and desktop browsers.

06 / Key System Features

• Multi-modal candidate interview pipeline with WebRTC video and audio capture
• High-accuracy speech-to-text transcription via OpenAI Whisper API
• Natural conversational voice question synthesis powered by OpenAI TTS
• Multi-dimensional AI scoring rubrics (Technical Depth, Communication, Tone & Sentiment)
• Asynchronous evaluation queue with polling mechanism to eliminate HTTP timeouts
• Automated candidate proctoring snapshots and CSV candidate export
• Fine-grained token credit budgeting and deduction management

07 / Outcome & Result

Reduced initial candidate screening time by 75%, delivered 98.5% transcription accuracy across multi-accent speech, maintained sub-3.2s async polling feedback, and achieved a 92% interview completion rate through a guided glassmorphic React interface.

08 / Future Improvements

• Implement real-time WebRTC bi-directional streaming for zero-latency AI interruption handling
• Integrate local on-device Whisper models via WebAssembly for offline and privacy-first transcription

09 / Technology Pipeline Stack

10 / Project Integrations & Repos