Generative AI & Full-Stack Engineer

The Opportunity

Build production-ready AI solutions for clients, from prototypes and copilots to integrated enterprise applications. You'll combine strong software engineering with practical experience deploying LLM-based systems safely and reliably.

What You'll Do

• Build AI-powered web applications, internal tools, APIs, and workflow automations.
• Integrate foundation-model APIs, retrieval-augmented generation (RAG), tool use, and agent workflows.
• Design secure, scalable application architectures and deployment pipelines.
• Evaluate model quality, latency, cost, reliability, and user experience.
• Connect AI systems to client data sources, business systems, and third-party services.
• Document technical decisions and collaborate closely with client and delivery teams.

What You Bring

• 4+ years of software engineering experience, including full-stack or backend development.
• Strong proficiency in Python, TypeScript/JavaScript, or similar languages.
• Hands-on experience with LLM application frameworks, vector databases, APIs, and cloud platforms.
• Knowledge of RAG, prompt engineering, evaluation, observability, and guardrail patterns.
• Experience with modern frontend frameworks and databases.
• A practical, delivery-oriented mindset; consulting experience is a plus.