Founder & Solutions Architect at Syncora Systems, building AI, automation, intelligent infrastructure & software systems

github

Manav Gawas • Peerlist

Engineered a high-throughput, fully concurrent voice AI streaming backend to solve the standard 1.5s+ Time-To-First-Audio (TTFA) latency bottleneck in conversational AI. By replacing sequential HTTP polling with a persistent full-duplex WebSocket architecture, the system achieves human-like reflexes with sub-300ms latency. Core Architectural Features: Concurrent Duplex Routing: Built a deterministic Go (Golang) backend utilizing Goroutines and Channels for thread-safe, non-blocking audio byte routing between the client and multiple AI inference endpoints. Semantic Chunking Buffer: Implemented a custom text-buffer that catches streaming LLM tokens and fires synthesis requests the exact millisecond it detects sentence-ending punctuation, eliminating robotic stuttering and maximizing throughput. Native Voice Activity Detection (VAD): Engineered zero-cost interruption handling using Go's context.Context cancellation. The system instantly detects user interruptions, kills mid-flight network requests to save compute, and flushes client-side audio queues for immediate responsiveness. Web Audio Sequencing: Developed a React/Next.js frontend leveraging the native browser AudioContext to queue and schedule incoming PCM WAV chunks with sub-millisecond precision.

Syncora Voice Core: Sub-300ms Conversational 

Engineered a high-speed data monitoring and alerting pipeline. Designed to watch concurrent data streams for specific market conditions and anomalies with minimal latency, ensuring deterministic alert execution under heavy network load. Core Focus: Anomaly detection, concurrent data ingestion, and alerting infrastructure.

Sentinel: Real-Time Market Monitoring System

Designed a microservices orchestrator to handle state management across concurrent nodes. Built the architecture to manage node registration, health-check pooling, and task distribution deterministically, ensuring high availability and system resilience against individual worker node failures. Showcase URL: https://github.com/ManavGawas/Distributed-Systems-Orchestrator

Fault-Tolerant Distributed Systems Orchestrat

Architected a secure, low-latency financial matching engine designed for hidden order execution. Focused on optimizing data ingestion pipelines and ensuring mathematical determinism for concurrent trade matching without state corruption.

Quantitative Dark Pool Execution Engine

Developed a full-stack platform optimizing volunteer coordination. Engineered location-based mapping features and secure authentication pipelines to match users with community needs efficiently and reliably. Core Focus: Client-server architecture, database schema design, and secure auth flows.

Smart Volunteer: Geo-Spatial Web Application

Engineered a highly concurrent, thread-safe backend routing core from scratch to handle heavy spatial queries. Implemented strict Euclidean geometry math functions and utilized RWMutexes to eliminate data races during state mutations. • Core Focus: Memory safety, lock-free architectures, and 95.2% test coverage.

Deterministic Spatial Ride-Matching Engine

Built an automated auditing tool designed to evaluate system vulnerabilities and enforce security compliance. Focused on secure data handling, threat modeling frameworks, and generating actionable compliance metrics for enterprise environments. • Core Focus: Vulnerability scanning, compliance automation, and secure coding practices.

Enterprise Cybersecurity Assessment Platform

Architected a low-latency infrastructure pipeline for deploying autonomous B2B voice agents. Optimized system architecture to achieve sub-300ms response times for AI voice interactions, eliminating operational bottlenecks for real-time lead qualification and scheduling. Core Focus: Distributed automation, latency optimization, and RevOps workflow engineering.

Real-Time AI Agent Deployment Pipeline

Developed a data-driven application for tracking physical optimization and hypertrophy metrics. Architected the database schema to handle complex relational data for workout splits, progressive overload mapping, and targeted user analytics. Core Focus: Relational database design, data persistence, and user-centric workflows.

Force Fitness: Optimization Tracking Applicat

Built a highly available, event-driven microservice architecture in Go to orchestrate autonomous AI workloads at scale. Durable Execution: Engineered a zero-data-loss pipeline using Temporal.io to guarantee state resurrection if a worker node crashes during multi-step LLM inference tasks. Semantic Caching: Integrated Qdrant Vector DB via gRPC to build a sub-15ms semantic interceptor, caching mathematically similar prompts at the edge to completely bypass redundant AI API compute costs. Event-Driven Decoupling: Separated client ingestion from execution using Apache Kafka for high-throughput message brokering and Redis for distributed L7 rate-limiting. Real-Time Telemetry: Eliminated HTTP polling bottlenecks by implementing Redis Pub/Sub combined with Server-Sent Events (SSE) for full-duplex, real-time client communication.