Generative AI Engineer

Robotics Technologies; Phoenix (AZ); On-site; USD 92,000 - 131,000; Full time

Job summary

Robotics Technologies in Phoenix, AZ seeks a Generative AI Engineer to design, implement, and operate scalable GenAI systems built on RAG architectures. You will develop end-to-end ingestion, embeddings, and retrieval pipelines, and deploy GenAI solutions in cloud environments.

You will work with languages and frameworks like Python, LangChain, LlamaIndex, and various LLMs, focusing on performance, security, and cost efficiency while collaborating with cross-functional teams.

Qualifications

• Hands-on experience with Generative AI and RAG workflows.
• Proficiency in Python.
• Experience with LangChain and LlamaIndex.
• Familiarity with vector databases and embeddings.
• Knowledge of REST APIs and cloud deployment.

Responsibilities

• Design scalable GenAI solutions using RAG architectures.
• Develop AI-powered apps with LLMs like GPT, Claude, Llama, Gemini.
• Build end-to-end data ingestion, embeddings, indexing, retrieval, and response pipelines.
• Refine prompts to optimize model performance and cost.
• Integrate vector databases and semantic search into GenAI apps.
• Collaborate with cross-functional teams to translate business needs into AI solutions.
• Monitor model accuracy, relevance, latency, and cost efficiency.
• Apply security, governance, and Responsible AI best practices.
• Deploy and maintain GenAI solutions in cloud environments.

Skills

Generative AI

RAG frameworks

Python

LLMs

LangChain

LlamaIndex

Prompt engineering

AI model evaluation

Vector databases

Embeddings

Semantic search

Information retrieval

REST APIs

Microservices

Cloud platforms

Docker

Kubernetes

CI/CD

DevOps

Tools

LangChain

LlamaIndex

Docker

Kubernetes

CI/CD

Job description

Robotics Technologies is seeking a Generative AI Engineer to design, implement, and operate scalable Generative AI systems built on RAG architectures. The role focuses on building end-to-end ingestion and retrieval workflows, integrating vector databases and semantic search, and deploying GenAI solutions in cloud environments for ongoing performance, cost, and reliability improvements.

Location: Phoenix, AZ (onsite)
Compensation: USD 81 - 81 per hour

What you will do

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

What you bring

• Strong experience with Generative AI and RAG frameworks.
• Proficiency in Python.
• Hands-on experience with LangChain, LlamaIndex, or similar orchestration frameworks.
• Experience working with LLMs and foundation models.
• Knowledge of prompt engineering and AI model evaluation.
• Experience with vector databases such as Pinecone, ChromaDB, Weaviate, FAISS, or Azure AI Search.
• Strong understanding of embeddings, semantic search, and information retrieval techniques.
• Experience with REST APIs, microservices, and cloud platforms including Azure, AWS, or GCP.
• Familiarity with Docker, Kubernetes, CI/CD, and DevOps practices.

Preferred qualifications

• Experience with AI Agents and agentic AI frameworks.
• Exposure to GraphRAG, knowledge graphs, and advanced retrieval techniques.
• Experience with MLOps and AI governance.
• Knowledge of Responsible AI and model monitoring frameworks.
• Experience developing enterprise-grade AI applications in large-scale environments.

Technologies

• RAG, Python, LangChain, LlamaIndex
• LLMs: GPT, Claude, Llama, Gemini
• Vector databases: Pinecone, ChromaDB, Weaviate, FAISS, Azure AI Search
• Embeddings, Semantic search, Information retrieval
• REST APIs, Microservices
• Cloud platforms: Azure, AWS, GCP
• Docker, Kubernetes, CI/CD, DevOps

Work authorization

• US Citizen
• Green Card
• OPT-EAD, CPT
• H-1B, H4-EAD
• Other