GID is a privately-held real estate company with over 60 years of experience in managing multifamily and industrial assets. The Applied AI Engineer will design and implement AI systems that enhance developer efficiency and improve code quality, while working across software engineering and AI systems design.
Responsibilities:
- AI System Design & SDLC Augmentation
- Define where and how AI augments each SDLC stage (plan, code, test, release, operate)
- Build agent workflows, RAG pipelines, structured reasoning chains, and prompt strategies tailored to engineering use cases
- Encode organizational standards—coding patterns, architecture rules, security requirements, and release policies—into AI behavior
- Developer Workflow Integration
- Integrate AI into developer environments (IDE extensions, PR bots, CI/CD checks, incident response flows)
- Build Full stack Apps using AI tools like Cursor and Claude Code
- Build and expose AI capabilities through FastAPI or similar API frameworks
- Collaborate with DevSecOps to ensure secure, reliable, and scalable deployment patterns for AI systems
- Quality, Safety & Optimization
- Validate AI outputs for correctness, hallucination risk, and alignment with business logic
- Continuously improve prompt performance, retrieval accuracy, reliability, and cost/latency efficiency
- Define human-in-the-loop steps, escalation paths, and UX patterns for safe AI deployment
- Cross-Functional Partnership
- Partner with the AI Platform Engineer to leverage Azure AI Foundry, Snowflake Cortex, vector stores, and model routing frameworks
- Partner with platform and application engineers to productionize AI-powered workflows and features
- Work with Product Managers to translate user requirements into technical AI solutions
Requirements:
- 4–7+ years of full stack software or platform engineering experience
- 2–4+ years applying AI in production environments
- Strong proficiency in Python and SQL
- Experience with prompt engineering, RAG, and multi agent systems
- Ability to reason about business logic, data correctness, and applied AI failure modes
- Familiarity with AI tools such as Claude, Claude Code, or Copilot for experimentation
- Experience with LLMs, embeddings, and vector databases
- Knowledge of agent frameworks or MCP-style tool integrations
- Experience partnering with Product Managers or platform engineers
- Familiarity with AI UX patterns and human-in-the-loop systems