AI product engineering · assessment
DeepDSA - AI Technical Interview & Assessment Platform
A microservices-based AI interview platform designed to scale to millions of concurrent users. The platform combines speech-to-text, LLM-powered natural language technical interviews, code evaluation, and skill scoring to improve assessment efficiency by 65%.
Outcome
Improved assessment efficiency by 65%.
Evaluation
The system was designed around assessment workflow efficiency and the separation of interview, execution, and scoring responsibilities.
Context
Technical interviews need to evaluate communication, reasoning, and code in one experience without turning the process into disconnected tools.
Contribution
Built a microservices-based interview platform combining speech-to-text, LLM interviewing, code evaluation, and skill scoring.
Architecture and workflow
Next.js interface · Redis and PostgreSQL · Speech-to-text · LLM interviewer · Code evaluation and skill scoring
Limitation
The public record does not claim a specific production concurrency benchmark or expose private evaluation data.