Generative AI/LLM Engineer

Public Storage•Frisco, TX

8d•Hybrid

About The Position

We are seeking a Generative AI / LLM Engineer with strong full-stack and Python development expertise to design, build, and deploy intelligent agents, Retrieval-Augmented Generation (RAG) systems, voice and image AI models, and automation workflows. This role is onsite in Frisco, TX and will work closely with product, engineering, and operations teams to deliver scalable, production-grade AI/Agent solutions that transform how Public Storage operates and engages with customers.

Requirements

Bachelor’s or Master’s in Computer Science, AI/ML, Data Science, or related discipline.
5+ years of professional Python development experience (APIs, microservices, automation).
Proven experience with LLMs (OpenAI, Anthropic, Meta, Mistral, etc.) and frameworks like LangChain or LlamaIndex.
Strong knowledge of RAG architectures, vector databases (Pinecone, Weaviate, Chroma, Milvus, Supabase), and semantic search.
Experience with TTS/STT systems (OpenAI Whisper, Coqui TTS, ElevenLabs).
Hands-on with generative image models (GPT-Image-1, Stable Diffusion, ComfyUI).
Proficiency with automation/orchestration platforms (n8n, Make, Zapier).
Cloud deployment experience (GCP, AWS, or Azure) for AI services.
Solid understanding of AI prompt engineering best practices.
Candidates must be authorized to work in the U.S. without restrictions or requiring sponsorship now or in the future.

Nice To Haves

Experience with containerization/orchestration (Docker, Kubernetes).
MLOps experience with continuous training and deployment workflows.
Frontend development skills (React, Next.js, or similar).
Prior experience in self-storage, real estate, or retail technology environments.

Responsibilities

Design, train, and deploy conversational and task-specific AI agents leveraging cutting-edge LLM architectures and tool integrations.
Build and optimize Retrieval-Augmented Generation systems for contextual, knowledge-rich AI responses.
Implement and integrate TTS (Text-to-Speech), STT (Speech-to-Text), and Whisper-based transcription pipelines.
Develop and integrate image generation, recognition, and analysis models for operational and customer-facing use cases.
Create workflow automations using tools like n8n, Make (Integromat), Zapier, and custom Python frameworks.
Build APIs, microservices, and interfaces to deliver AI solutions end-to-end, from data ingestion to UI.
Monitor, evaluate, and improve AI model performance for accuracy, latency, and scalability.
Partner with cross-functional teams to integrate AI capabilities into business processes and customer products.
Ensure AI solutions adhere to corporate security policies, privacy regulations, and ethical AI principles.