Grounded Enterprise AI Engineer — GenAI & RAG Apps

RADcube; Indianapolis (IN); Hybrid; USD 120,000 - 180,000; Full time

Job summary

RADcube in Indianapolis, IN is seeking an AI Context Developer to build enterprise GenAI applications that securely use organizational data, documents, and business context. You will create context and retrieval layers to empower LLMs and AI agents within client workflows, contributing to a hands-on delivery model.

Ideal candidates will have strong Python and LLM development experience, experience with RAG pipelines, vector search, and API/microservice design.

Qualifications

• Strong Python and LLM application development experience.
• RAG, embeddings, and vector search or vector databases.
• Prompt and context engineering.
• Document ingestion, chunking, retrieval, and reranking.
• APIs and microservices.
• LLM evaluation and agentic workflows.
• Comfortable meeting business teams and explaining AI solutions clearly.

Responsibilities

• Build LLM applications, RAG pipelines, and agentic workflows.
• Build document ingestion, chunking, embeddings, and vector search.
• Implement retrieval and reranking, and design prompt and context engineering strategies.
• Build APIs and microservices that serve AI capabilities.
• Evaluate and monitor output quality, accuracy, and grounding.
• Apply enterprise security and governance controls to AI solutions.
• Meet business teams to identify what additional enterprise knowledge or data could enable new AI use cases.
• Contribute to the growth of the overall engagement.

Skills

Python

LLM development

RAG / vector search

Prompt engineering

Document ingestion

APIs / microservices

LLM evaluation

Business-facing communication

Tools

Databricks

MLflow

LangChain

LlamaIndex

NVIDIA AI ecosystem

LangGraph

Knowledge graphs

Job description

RADcube in Indianapolis, IN is seeking an AI Context Developer to build enterprise GenAI applications that securely use organizational data, documents, and business context. You will create context and retrieval layers to empower LLMs and AI agents within client workflows, contributing to a hands-on delivery model.

Ideal candidates will have strong Python and LLM development experience, experience with RAG pipelines, vector search, and API/microservice design.