AI FullStack Engineer

Location:

Preferable Chicago (Remote also works)

Job Type :
Contract

We are seeking a highly autonomous full‑stack engineer focused on building and deploying Generative AI applications and AI agents. This individual will work across frontend and backend, design and integrate LLM‑powered features, and leverage Azure cloud services—including vector search—along with modern multi‑cloud AI platforms such as Vertex AI and OpenAI.

• Strong experience with modern frontend + backend stacks (e.g., React, Node.js, Python, Type Script, FastAPI, etc.)
• Understands API design, modular architecture, and secure data flows

• Hands‑on experience calling LLMs via API, including prompt orchestration and function calling
• Skilled at indexing and retrieving data from vector databases (e.g., Azure AI Search hybrid + vector search)
• Experience integrating and fine‑tuning models across:
  • Google Vertex AI (Gemini models, embeddings, vector search)
  • OpenAI platform APIs
• Ability to design intelligent workflows powered by LLMs, embeddings, and retrieval pipelines

• Experience building AI agents, including:
  • Attaching skills/plugins exposed as APIs
  • Using function calling / OpenAI tools paradigm
• Familiarity with Semantic Kernel and Azure AI Agents Framework
• Knowledge of MCP (Model Context Protocol) to expose internal systems and APIs as agent capabilities

• Proficient with Git and repository branching strategies
• Builds CI/CD pipelines and deploys workloads to Azure
• Monitoring, observability, and strong operational mindset

• Proficient with AI coding assistants (Cursor, Git Hub Copilot, etc.) to maximize autonomy and delivery velocity

• Operates independently, takes ownership from concept to deployment
• Problem‑solver with strong communication skills
• Thrives in fast‑paced environments and continuously learns
• Thinks proactively about reliability, performance, and security