Full Stack Engineer (AI)
Key ResponsibilitiesFull-Stack Execution: Write clean, high-performance, and maintainable code across the stack using C# (.NET 8+) for high-throughput backend services and Svelte / SvelteKit or similar frontend framework with TypeScript for dynamic, responsive interfaces.AI-Powered Commerce Architecture: Architect and scale secure, AI-native applications that optimize digital storefront conversion, dynamic merchandising, and end-to-end personalization.Agentic Workflows & Multi-Agent Systems: Design and orchestrate autonomous AI agents using advanced function calling and tool use across frontier models (OpenAI, Anthropic, Gemini).Protocol & Data Integration: Leverage the Model Context Protocol (MCP) to securely bridge LLMs with enterprise systems, real-time data, loyalty platforms, and CRM platforms.Dual-Cloud & Distributed Systems: Deploy, monitor, and scale workloads across Microsoft Azure (Azure OpenAI, App Services, Cosmos DB, Service Bus) and GCP, ensuring low latency, high availability, and cost efficiency under peak load.Architecture, Safety & Quality: Drive end-to-end system design, establish rigorous CI/CD and testing standards (xUnit, Playwright, Vitest), and enforce AI safety, OWASP Top 10 for LLMs, and data privacy guardrails.Required Skills & QualificationsTechnical Core & CloudBackend: Deep expertise in C# and modern .NET (.NET Core / .NET 8+) building enterprise RESTful APIs, asynchronous services, and clean architectures.Frontend: Proven track record building high-performance, accessible web applications with SvelteKit or modern Svelte (plus TypeScript and modern CSS).Cloud Platforms: Hands-on experience architecting and operating production workloads in Microsoft Azure (primary) and Google Cloud Platform (GCP).Data Stores: Strong command of relational databases (Azure SQL / SQL Server, PostgreSQL) and document/NoSQL stores (Azure Cosmos DB), including indexing and schema design.AI & Agentic SystemsAgentic Frameworks: Proven experience designing multi-agent orchestrations, autonomous task execution, and complex function-calling/tool-use pipelines.Model Context Protocol (MCP): Hands-on experience integrating systems via the MCP framework for secure, standardized LLM tooling.LLMs & RAG: Deep understanding of prompting strategies, semantic caching, vector indexing, and Retrieval-Augmented Generation (RAG) using OpenAI, Anthropic, or Gemini APIs.Professional Experience8+ years of professional software engineering experience.3+ years of dedicated experience building and scaling production-grade AI-native or LLM-powered applications.Strong background in System Design, specifically balancing the trade-offs of latency, cost, and accuracy when integrating AI into revenue-generating e-commerce flows.Proven success as an individual contributor in fast-paced, agile environments.