Generative AI Engineer — RAG & LLM Solutions

Robotics Technologies LLC; Phoenix (AZ); On-site; USD 130,000 - 190,000; Full time

Job summary

Robotics Technologies LLC seeks a talented Generative AI Engineer to design scalable AI solutions using RAG architectures in our Phoenix office. You will build end-to-end data ingestion, embedding, indexing, retrieval, and response-generation pipelines, and optimize prompts to improve model performance.

You will collaborate with product and engineering teams to translate business needs into AI-driven applications, evaluate latency and cost, implement governance and security best practices, and

Qualifications

• Experience designing and deploying GenAI solutions with RAG architectures.
• Proficiency in Python and AI model integration.
• Hands-on experience with vector databases and semantic search.
• Familiarity with cloud platforms and DevOps practices.

Responsibilities

• Design and implement scalable Generative AI solutions using RAG architectures.
• Develop AI-powered applications leveraging LLMs such as GPT, Claude, Llama, and Gemini.
• Build end-to-end data ingestion, embedding, indexing, retrieval, and response-generation pipelines.
• Develop and optimize prompt engineering strategies for improved model performance.
• Integrate vector databases and semantic search capabilities into AI applications.
• Collaborate with cross-functional teams to translate business requirements into AI-driven solutions.
• Monitor, evaluate, and improve model accuracy, relevance, latency, and cost efficiency.
• Implement security, governance, and Responsible AI best practices.
• Deploy and maintain GenAI solutions in cloud environments.

Skills

Generative AI

RAG frameworks

Python

LangChain / LlamaIndex

LLMs / foundation models

Prompt engineering

Vector databases

REST APIs & Cloud

Docker / Kubernetes

Job description

Robotics Technologies LLC seeks a talented Generative AI Engineer to design scalable AI solutions using RAG architectures in our Phoenix office. You will build end-to-end data ingestion, embedding, indexing, retrieval, and response-generation pipelines, and optimize prompts to improve model performance.

You will collaborate with product and engineering teams to translate business needs into AI-driven applications, evaluate latency and cost, implement governance and security best practices, and