Lead Software Engineer Agentic AI & Voice Platforms

Employment : 1-year contract Lead Software Engineer Agentic AI & Voice Platforms We are seeking a Lead Software Engineer with a deep expertise in Python and Agentic AI to lead the development of next-generation voice-first intelligent applications . This role requires hands-on technical leadership in architecting, deploying, and scaling agentic AI systems across public cloud, private cloud, and bare-metal environments. Responsibilities Lead and mentor a team of engineers focused on building agentic AIdriven voice applications. Provide platform-level technical leadership and oversight for frontend (React/TypeScript) and backend (Python/TypeScript) application development. Drive platform development initiatives, ensuring scalability, maintainability, and cross-service integration. Own the full software development lifecycle (SDLC) from design and prototyping to deployment and operations. Architect, design, and implement scalable, secure AI workflows and applications in Python. Build and orchestrate multi-agent systems with capabilities such as tool calling, persistent memory, reasoning, and real-time interaction. Integrate and extend frameworks such as LangGraph, Semantic Kernel, CrewAI, or AutoGen for agent orchestration. Develop and optimize voice-based agent applications , including speech-to-text, text-to-speech, and conversational orchestration. Collaborate with AI researchers, product managers, and designers to translate product requirements into robust, user-centric AI systems. Design deployment strategies for GenAI workloads across public clouds (AWS, GCP, Azure), private clouds, and bare-metal infrastructure. Implement and optimize event-driven, low-latency systems for real-time communication (queues, WebSockets, gRPC, or NATS). Lead CI/CD and DevOps practices , ensuring high reliability and efficient deployment pipelines. Encourage best practices in documentation, architecture, and knowledge sharing within the team. Stay ahead of the curve on Agentic AI research, voice interfaces, and emerging developer tools . Requirements 6+ years of experience in backend/software engineering, with strong expertise in Python . Proven experience architecting and deploying agentic AI systems in production. Strong knowledge of voice application development : speech recognition (STT), natural language processing, and text-to-speech pipelines. Hands-on work with voice agent frameworks or telephony APIs (Twilio, WebRTC, SIP, etc.) and experience with LiveKit (must-have). Experience with vector databases, RAG pipelines, or fine-tuning LLMs . Hands-on experience with frameworks like LangGraph, Semantic Kernel, CrewAI, AutoGen , or equivalents. Solid understanding of public cloud platforms (AWS, GCP, Azure) and deployment in private cloud or bare-metal environments . Proven ability to understand platform development and lead full-stack solutions that integrate React, Python, and TypeScript. Experience with event-driven architectures and real-time communication systems. Skilled in CI/CD, DevOps, containerization (Docker/Kubernetes), and infrastructure-as-code (Terraform or similar). Strong architectural thinking, leadership, and problem-solving abilities. Excellent communication skills in English, both written and verbal. Bonus Familiarity with multi-modal AI systems (voice + vision + text). Contributions to open-source AI/voice projects or participation in agentic AI research initiatives.