Generative AI & LLM Engineer: RAG, Agents, & Automation

Public Storage

Frisco (TX)

On-site

USD 150,000 - 190,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Office in Frisco, TX

Up to 3 remote days per month

Job summary

Public Storage is seeking a Generative AI / LLM Engineer to design, build, and deploy AI agents, RAG pipelines, voice and image AI models, and automation workflows. Onsite in Frisco, TX, you will partner with product, engineering, and operations to deliver scalable AI solutions for customer engagement and operations.

The role covers full-stack AI delivery, performance optimization, and security/compliance considerations, with collaboration across teams.

Qualifications

Bachelor’s or Master’s in CS/AI/DS or related field.
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, and semantic search.
Experience with TTS/STT systems and generative image models.

Responsibilities

LLM Agent Development: Design, train, and deploy conversational and task-specific AI agents with tool integrations.
RAG Pipelines: Build and optimize Retrieval-Augmented Generation systems for contextual responses.
Voice & Speech AI: Implement and integrate TTS, STT, and Whisper-based transcription pipelines.
Generative Image AI: Develop and integrate image generation, recognition, and analysis models.
Automation & Orchestration: Create workflow automations using n8n, Make, Zapier, and custom Python frameworks.
Full-Stack AI Delivery: Build APIs, microservices, and interfaces end-to-end, from data ingestion to UI.
Performance Optimization: Monitor and improve model performance for accuracy and latency.
Collaboration: Work with cross-functional teams to integrate AI into business processes.