Full Stack Engineer

About Us

Xtnsion AI builds the Agentic CX Layer for modern SMBs — AI voice and chat agents that don’t just respond, but understand intent, retrieve context, take actions, and close loops.

Our platform autonomously manages bookings, lead follow-ups, CRM updates, and customer support workflows across phone and chat. We work closely with healthcare clinics and fast-growing D2C brands, where reliability, real-time performance, and system correctness truly matter.

We are now hiring our first full-stack engineer to partner directly with the founder and take the platform from prototype → production → scale.

About the Role

You will own the entire engineering surface area of Xtnsion AI — architecture, backend services, agent workflows, integrations, dashboards, infrastructure, deployments, and production reliability.

This is a hands-on, end-to-end role in a lean startup environment, where ownership, judgement, and execution speed matter more than perfect specs.

This role is ideal for someone who has built real products 0→1, enjoys thinking in systems, and is comfortable carrying work across the finish line — not just implementing isolated features. This is not a research role or a model-tuning role.

What You’ll Build

• The core backend of Xtnsion AI - Scalable APIs, authentication, multi-tenant architecture, and data models in Python/FastAPI that form the foundation of the platform.
• The agentic intelligence layer - LLM-driven workflows including tool execution, RAG pipelines, vector search, memory management, and reasoning logic that enable autonomous, multi-step actions.
• Deep, production-grade integrations - Systems integrating with EHRs, CRMs, API integrations, and helpdesks — enabling real operational efficiency for customers.
• Build real-time voice and chat AI agents
• Customer-facing dashboards and internal tools - Built in React/Next.js — workflow configuration, logs, analytics, and conversation visibility for customers and operators.
• Infrastructure and reliability - Dockerised environments, CI/CD pipelines, monitoring, observability, and cloud deployments on AWS/Azure, with a focus on performance, uptime, and debuggability.
• Production-ready systems end-to-end - From system design and implementation to testing, debugging, latency optimisation, and operating the platform in real customer environments.

What You Bring

• 3–7+ years of engineering experience
• Strong backend experience with Python and FastAPI
• Full-stack capability with React/Next.js and modern frontend practices
• Solid understanding of API design, data modelling, and system architecture
• Hands-on experience with LLMs and agentic systems — including workflow orchestration, tool execution, RAG, memory, and vector search
• Experience building real-time or near-real-time AI systems (voice and/or chat)
• Hands-on experience with Docker, CI/CD, and deploying systems on AWS or Azure
• Comfortable integrating third-party APIs and working with webhooks
• Strong debugging instincts and a bias toward production-ready engineering
• Proven ability to operate in 0→1, lean startup environments with high ownership

Nice to have

• Experience building end-to-end AI systems — from system design and orchestration to production deployment and real-world usage
• Familiarity with real-time conversational AI systems across voice and chat, including multi-channel messaging experiences
• Previous experience as an early hire or founding engineer in a startup environment

What will make you successful here

• You’ve built products end-to-end, not just components
• You’re comfortable owning design decisions and technical trade-offs
• You move fast without breaking fundamentals
• You think about reliability, observability, and real-world usage — not just happy paths
• You’re energized by ambiguity and ownership, not blocked by it

Why this role matters

This is a defining engineering role at Xtnsion AI.

The systems you design and ship will become the backbone of how real businesses interact with AI every day. You’ll work directly with the founder, influence product and architecture decisions early, and help shape the technical DNA of the company as we scale.