Mevini Munaweeraa@mevinimunaweera34523

TalentCore AI is an enterprise-grade, full-stack recruitment ecosystem designed to eliminate hiring bias and automate deep technical candidate screening. Traditional recruitment workflows rely on flat keyword filtering or static, generic question banks that fail to capture an engineer's true architectural depth. This platform completely overhauls that dynamic using a decoupled, multi-stage asynchronous multi-agent framework built with CrewAI, FastAPI, and React. When a candidate uploads a CV PDF against an active job opening, the background worker thread pool activates Crew 1. A CV Scanner Agent performs structural data sweeps to detect technical blind spots, passing context to a Primary Interviewer Agent that crafts 3 deeply specific scenario questions tailored explicitly to that candidate. Responses are captured via a live web interface hosting a GPU-accelerated CSS processing orb. Upon submission, Crew 2 (Follow-Up Interviewer) executes a cross-examination to probe surface-level claims, streaming context-aware follow-up questions. Finally, Crew 3 (Grading Panel) reviews the full transcript, scoring the candidate across a strict 4-dimension rubric and backing up every metric using verbatim candidate quotes to prevent AI hallucinations. To maintain strict candidate privacy and absolute corporate data sovereignty, TalentCore AI features a dual-routing architecture. By bypassing third-party cloud API dependencies, the entire multi-agent orchestration pool can execute entirely on-premise. The backend offloads heavy matrix computations to open-source local LLMs (like Llama 3) accelerated natively by the AMD ROCm™ software platform across AMD Radeon™ workstation GPUs and AMD Ryzen™ AI neural processing units, achieving single-digit millisecond query targets under high concurrency.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.