ch RwSRDkAv – GenAI & RAG (Multiple Levels) — Charlotte Metro

This is a full-time, direct-hire role (not contract). It is open to US Citizens, Green Card holders, and H-1B holders with at least three years remaining on their visa or an approved I-140.

About the Role

s7R is partnering with a global financial institution to hire AI Engineers at multiple levels to help design and build its enterprise GenAI platform. This is a high-impact, hands-on role at the center of the bank’s AI strategy.

You will build production RAG pipelines that give teams across the bank accurate, well-sourced answers from their own documents and data. You’ll own retrieval, chunking and embedding strategies, develop agentic workflows using tools like LangGraph, and build the LLM services that other teams rely on. You’ll work primarily on Azure, alongside Databricks, and partner closely with Architecture, Technology, Data and business stakeholders.

This is not a research role or a pure architecture role. We want engineers who can design solutions, write the code, and get them into production in a regulated environment.

What You’ll Do

• Design, build and maintain production-grade RAG pipelines, from document ingestion, chunking and embeddings through retrieval, reranking and grounded answer generation

• Improve retrieval quality using hybrid search, rerankers, metadata filtering, query rewriting and chunking strategies, measured with clear evaluation metrics

• Build and maintain agentic workflows using LangGraph and similar frameworks, with tool calling, state management and human-in-the-loop controls

• Develop REST and WebSocket-based LLM services for applications across the bank

• Establish evaluation, monitoring and guardrails for LLM applications in production, including groundedness, hallucination, latency and cost

• Apply LLMOps practices for versioning, observability, testing and security in a regulated environment

• Evaluate emerging GenAI technologies and help educate wider engineering teams on GenAI techniques and best practices

What We’re Looking For

• Bachelor’s degree in Computer Science, Machine Learning, Data Science or a related field

• 3+ years of hands-on experience developing, deploying and maintaining GenAI or advanced ML solutions in production

• Strong Python skills and experience with GenAI frameworks and tools such as LangGraph, LangChain, LlamaIndex or Haystack

• Hands-on RAG experience, including chunking strategies, embedding models and vector search (e.g., Azure AI Search, Databricks Vector Search, Pinecone or pgvector)

• Experience evaluating LLM applications (e.g., golden datasets, LLM-as-judge, RAGAS) and monitoring them in production

• Experience with Azure AI services such as Azure OpenAI and Azure AI Document Intelligence

• Proven experience building and deploying RESTful services, containerization and automated CI/CD

• Excellent communication skills, with the ability to partner with technical and non-technical stakeholders

Nice to Have

• Experience with Databricks and MLflow

• Fine-tuning, GraphRAG or agent protocols such as MCP

• Experience in banking or another regulated industry

s7R is proud to be an equal opportunity recruiter. We are committed to fostering an inclusive recruitment process and ensuring equal consideration for all applicants regardless of gender, age, disability, religion, sexual orientation, marital status, or race.