Software Engineer @ Convai
Working on FaaS, tool execution, and low-latency AI infrastructure
Python • Go • Distributed Systems • WebRTC • Kubernetes
- Real-time conversational AI systems with low-latency streaming
- Functions-as-a-Service (FaaS) for dynamic LLM tool execution
- Agent orchestration pipelines (tool calling, execution, state management)
- Scalable infrastructure for interactive AI experiences (WebRTC, autoscaling)
- Built real-time, low-latency multimodal AI agents using WebRTC for live interaction
- Architected an in-house FaaS platform for AI agent tool execution
- Built a stateful autoscaler for real-time pixel streaming systems
- Designed APIs powering interactive AI experiences over live streams
- Handled production-scale data migrations for backend systems
- Languages: Python, Go, TypeScript
- AI/LLMs: RAG, Agent Architectures, Tool Calling
- Infra: Kubernetes, Distributed Systems, WebRTC
- Backend: FastAPI, gRPC, Event-driven systems
- Advanced LLM agent architectures
- Real-time AI infrastructure
- Building production-grade AI systems (not just demos)
I build systems that actually run in production — not just prototypes.
- 💼 LinkedIn: https://www.linkedin.com/in/md-manzer-alam-0ba00280/
- 📧 Email: 18preneur@gmail.com