APPLIED AI ENGINEER (1042) - Department of Technology

We are a small, mission-driven team leading responsible AI adoption across City government within DT.  

We work on:  

1.  Testing and making self-service AI tools available to other departments, 
2. Setting technical standards for safe and responsible AI use, and 
3. Building and experimenting with prototypes that demonstrate the potential of applied AI. 

As our Applied AI Engineer, your primary focus will be designing and backend AI cloud infrastructure needed to power AI services. This includes building ingestion pipelines, managing vector databases, integrating LLM APIs, and ensuring backend systems are reliable, observable, scalable, and safe. 

This role is hands-on, creative, and highly collaborative — ideal for someone who enjoys working at the intersection of technology, product, and impact.

Key Responsibilities:

• Build and manage RAG infrastructure and other cloud tools as needed (e.g., ingestion pipelines, embedding services, retrieval APIs, orchestration).
• Deploy and maintain vector databases and integrate them with AI services.
• Develop APIs and backend services that connect prototypes to LLMs and retrieval systems.
• Implement observability practices including monitoring, logging, alerting, and performance metrics to ensure system reliability and transparency.
• Use frameworks like LangChain, LlamaIndex, and related libraries to orchestrate retrieval workflows, agents, and hybrid pipelines.
• Ensure system scalability and resilience, with production-ready practices.
• Collaborate with the AI Product Engineer to integrate backend services with front-end applications and user pilots.
• Contribute to standards for safe, responsible AI adoption (data governance, security, and compliance).
• Experiment with new backend, platform, and cloud tools to stay current with the fast-evolving AI ecosystem.