Generative AI/LLM Engineer
Core
Design, build, and deploy intelligent agents, RAG systems, voice/image AI models, and automation workflows to transform customer engagement and internal operations.
Role type
Senior Generative AI/LLM Engineer (Full-Stack)
Builds
Scalable production-grade AI/Agent solutions, conversational agents, RAG pipelines, voice/image models, and automated workflows.
Domain
Self-storage / Real Estate / Generative AI
Deliverable
production ML models | product features | infrastructure
Required skills
Python development, LLM architecture (OpenAI, Anthropic, Meta, Mistral), LangChain, LlamaIndex, RAG architectures, vector databases, TTS/STT integration, generative image models, automation orchestration, cloud deployment, prompt engineering
Preferred skills
Containerization (Docker, Kubernetes), MLOps, Frontend development (React, Next.js), Self-storage/Real Estate domain experience
Technologies
OpenAI, Anthropic, Meta, Mistral, LangChain, LlamaIndex, Pinecone, Weaviate, Chroma, Milvus, Supabase, Whisper, Coqui TTS, ElevenLabs, GPT-Image-1, Stable Diffusion, ComfyUI, n8n, Make, Zapier, GCP, AWS, Azure, Docker, Kubernetes, React, Next.js
Responsibilities
Design and deploy conversational and task-specific AI agents; Build and optimize RAG systems for contextual responses; Implement TTS/STT and generative image models; Create workflow automations using orchestration platforms; Build APIs and microservices for end-to-end AI delivery; Monitor and optimize AI model performance for accuracy and scalability.
Seniority
Senior, hands-on IC