- Company Name
- City and County of San Francisco
- Job Title
- APPLIED AI ENGINEER (1042) - Department of Technology
- Job Description
-
**Job Title**
Applied AI Engineer
**Role Summary**
Design, build, and maintain scalable cloud‑based AI infrastructure that powers responsible AI services for city government. Responsibilities include developing ingestion pipelines, managing vector databases, integrating large‑language‑model (LLM) APIs, and implementing observability, security, and compliance controls.
**Expectations**
* Deliver robust, production‑ready back‑end systems that scale with demand.
* Champion data‑governance, security, and responsible‑AI best practices.
* Collaborate closely with product, engineering, and domain teams to align AI solutions with city goals.
* Stay current with emerging AI platforms, tools, and cloud technologies.
**Key Responsibilities**
* Build and manage Retrieval‑Augmented Generation (RAG) infrastructure, ingestion pipelines, and embedding services.
* Deploy, configure, and maintain vector databases (e.g., Pinecone, Chroma, Weaviate) and integrate them with AI services.
* Develop RESTful APIs and back‑end services that connect LLMs and retrieval systems to prototypes.
* Implement observability practices: monitoring, logging, alerting, and performance metric collection for system reliability and transparency.
* Orchestrate retrieval workflows, agents, and hybrid pipelines using frameworks such as LangChain and LlamaIndex.
* Ensure scalability, resilience, and production‑readiness of all back‑end components.
* Collaborate with AI Product Engineers to integrate backend features with front‑end applications and pilot deployments.
* Contribute to organizational AI standards covering data governance, security, and compliance.
* Experiment with and evaluate new backend, platform, and cloud tools to keep architecture up‑to‑date.
**Required Skills**
* Strong backend development expertise in Python (or similar).
* Experience with cloud platforms (AWS, Azure, GCP) and container orchestration (Docker, Kubernetes).
* Proficiency with vector databases and similarity search.
* Familiarity with LLM APIs (OpenAI, Anthropic, Cohere, etc.) and prompt engineering.
* Hands‑on knowledge of RAG architectures and retrieval frameworks (LangChain, LlamaIndex).
* Demonstrated ability to design observability, logging, monitoring, and alerting pipelines.
* Understanding of data‑governance, security, and compliance in a public‑sector context.
* Strong problem‑solving, communication, and collaboration skills.
**Required Education & Certifications**
* Bachelor’s degree in Computer Science, Engineering, or a related field (or equivalent experience).
* 3+ years of experience building production AI or data‑intensive back‑end systems.
* Cloud certification (AWS Solutions Architect, Azure Solutions Architect, GCP Professional Cloud Architect) preferred but not mandatory.
San francisco, United states
Hybrid
26-11-2025