Priyansh Aggarwal

About

Built core perception and decision layers for a 3D AI-powered interactive avatar/agent with a robotics-like perception–reasoning–action loop, combining computer vision, NLP, and real-time response. Focused on making multimodal inputs robust (normalization, intent + emotion signal fusion) and improving real-time performance via instrumentation, profiling, and parallelization; also designed distributed, loosely coupled state-based communication and deployed services with Docker.

Key Strengths

• Built multimodal perception pipeline combining vision, speech/text, intent, and emotion context
• Improved robustness to noisy/ambiguous user input via normalization and cleaning layers
• Reduced emotion-model noise by moving from single-model prediction to fused multi-signal approach
• Data-driven performance debugging using end-to-end instrumentation and stage-level latency profiling
• Latency optimization through parallelizing non-dependent pipeline stages
• Designed loosely coupled, asynchronous, state-based communication for distributed heterogeneous components
• Containerized AI services with Docker for consistent deployment and dependency isolation
• Created simulation/stress-test environments to evaluate behavior and latency under failure/load conditions

Experience

Education

Skills

Languages