Senior Back End Developer

About This Role

Company Description

Hams.AI is an AI company building a full enterprise automation platform, enabling organizations to automate customer interactions, operational tasks, data-driven decisions, and service processes across voice, chat, WhatsApp, and digital channels.

Our platform focuses on real-time execution, turning enterprise workflows into automated actions across systems with measurable reliability, speed, and control at scale.

Hams is expanding rapidly across multiple industries in the region, and we are looking for deep backend engineering talent to strengthen our platform core.

About the Role

We're building a production-grade platform for deploying enterprise AI-powered voice and chat agents at scale. Think: real-time voice bots that handle inbound/outbound calls, multi-agent orchestration, knowledge base retrieval, and telephony integration — all with sub-100ms latency requirements.

This isn't a wrapper around an LLM API. This is deep systems engineering across real-time audio, distributed computing, and AI orchestration.

What You'll Own

• Real-time Voice Pipeline — Audio processing with self-deployed STT/TTS models and LLM inference running concurrently across hundreds of simultaneous calls
• Multi-Agent Orchestration — Multi-agent coordination, conversation flow state machines, and handoff logic between specialized AI agents
• Distributed Systems at Scale — Task queues, pub/sub messaging, async database operations, process-per-session isolation, and graceful shutdown under load
• Telephony & WebRTC — SIP trunk management, PBX integration, real-time media streaming
• RAG & Knowledge Bases — Vector search, document chunking pipelines, and embedding management
• Multi-Tenant Architecture — Secure data isolation, encrypted credential management, and enterprise webhook delivery

Our Stack

Backend: Python, async web framework, async ORM, distributed task queue, in-memory data store, relational database

AI/ML: LLM orchestration framework, multi-agent graph framework, NLP libraries, ML model inference runtime

Voice: Real-time audio processing framework, WebRTC media server, PBX/SIP integration, self-deployed STT/TTS

Infra: Containers, orchestration, cloud storage, error tracking, distributed tracing, database migrations

Data: Vector database, relational DB with flexible schema, in-memory store for sessions/queues

What We're Looking For

10+ years of software engineering experience, with deep expertise in Python and distributed systems

Hands-on experience with real-time audio/video processing or VoIP/telephony systems

Strong background in async Python (asyncio and async frameworks)

Experience building and scaling multi-tenant SaaS platforms

Comfort with LLM orchestration — prompt engineering, agent frameworks, RAG pipelines

Track record of owning systems end-to-end: from database schema design to production monitoring

Experience with distributed task processing and message queues

Experience with self-deploying and managing STT/TTS models on server infrastructure

Bonus Points

Background in real-time audio frameworks and WebRTC media servers

• Experience with PBX/SIP telephony integration
• Speech processing model deployment and optimization
• Multi-language voice AI experience (Arabic, etc.)
• Prior founding/early-stage startup experience

Apply here:

https://form.asana.com/?k=yE2HX1zQr8rh77JA5LWmkw&d=1210838775195077