Full-Stack + AI

Intelligent Interview System

Low-latency candidate evaluation platform utilizing multi-agent AI consensus pipelines.

MERN StackGoogle Gemini APIWebRTCRedisBullMQSocket.ioMonaco Editor
01

Problem

Existing technical hiring platforms face functional fragmentation, scalability constraints under high concurrent user loads, and static assessments that fail to adapt in real-time to candidate performance.

02

Approach

Co-architected a full-stack low-latency platform using the MERN stack and Google Gemini API. Engineered a multi-agent MockLLM framework to dynamically adjust questioning, backed by Redis caching and BullMQ job queues for async orchestration. Integrated WebRTC and Socket.io with Monaco Editor for a real-time collaborative workspace.

03

Outcome

Delivered bidirectional code synchronization with <70ms latency and a multi-language code execution engine boasting a 1.4s average response time. Reduced overall API latency by 46% (890ms to 420ms) and improved candidate answer quality by 12.3% during pilot evaluations.

Technical Highlights

(7)
  • 01

    Multi-agent MockLLM framework dynamically adjusts questioning difficulty based on real-time candidate performance analysis

  • 02

    WebRTC + Socket.io integration delivers bidirectional code synchronization with <70ms latency

  • 03

    Monaco Editor provides full IDE experience with syntax highlighting and multi-language support

  • 04

    Redis caching + BullMQ job queues handle async orchestration and high concurrent loads

  • 05

    Multi-language code execution engine with 1.4s average response time

  • 06

    API latency reduced by 46% (890ms → 420ms)

  • 07

    Candidate answer quality improved by 12.3% in pilot evaluations

Kumar Priyam — AI Engineer · SDE · Data Engineer