AI Engineer (GenAI) Mid level - 100% Remote

JOB TITLE: Mid level Gen AI Engineer.

One of our hospitality and gaming customer based out of Las Vegas, NV is looking for a Generative AI Engineer to drive the development of cutting-edge AI applications, including RAG-based and agentic systems that process data from structured, unstructured sources, images, and PDFs.

Key Responsibilities

• Design and implement RAG pipelines end-to-end, including document ingestion, chunking, embedding, retrieval, and response generation for well-scoped product features or internal tools.
• Build and maintain LangGraph-based agents, modeling workflows as graphs (nodes, edges, conditional branches, loops) and integrating tools, retrievers, and external APIs.
• Implement and operate MCP servers that expose tools/resources to LLM hosts, including request/response handling, basic error handling, and logging.
• Integrate with LLM providers (e.g., Azure OpenAI, Databricks) and manage prompts, model configurations, and context windows for RAG-style interactions.
• Work with vector stores (e.g., Azure AI Search) to set up indexes, tune similarity search, and manage metadata for retrieval.
• Contribute to data ingestion pipelines for RAG (file connectors, text extraction, cleaning, metadata enrichment) in collaboration with data/platform teams.
• Build and productionize GenAI and RAG-style workloads on Databricks, leveraging tools such as Databricks Genie / AI Assistant for SQL, notebooks, and pipeline development, and integrating Databricks-native vector search or ML flows where appropriate.
• Design and implement AI-powered analytics and applications on Snowflake, using Snowflake Cortex capabilities (built-in LLM functions, embeddings, and vector search) as part of RAG and agent architectures.
• Add observability to agents, RAG components, and MCP servers (logging, tracing, metrics), and use these to debug failures, latency issues, and incorrect tool usage.
• Collaborate with product managers and senior engineers to translate requirements into technical designs and incremental delivery plans.
• Participate in code reviews, testing, and documentation, improving reliability, maintainability, and clarity of RAG, LangGraph, Databricks, and Snowflake-related codebases.
• Support security and compliance efforts by following established best practices around authentication, authorization, secrets management, and safe tool usage across cloud platforms.

Required Qualifications & Skills

• 5+ years of professional software engineering experience, with strong proficiency in Python (typing, packaging, testing, logging, async IO, REST APIs using frameworks like FastAPI/Flask).
• Hands-on experience building at least one RAG-style application or search/QA system that uses embeddings and retrieval over private or domain-specific data.
• Practical experience with vector databases or similarity search libraries, including index creation and query tuning.
• Experience with LangChain (or similar orchestration frameworks) and working knowledge of LangGraph concepts such as state, nodes, edges, and graph-based flows.
• Demonstrated ability to build and maintain agents that call external tools/APIs, handle multi-step reasoning, and manage conversation or workflow state.
• Familiarity with Model Context Protocol (MCP) concepts and at least some hands-on work with implementing or integrating an MCP server or similar tool-bridge.
• Solid understanding of prompting for RAG, including how to insert retrieved context, structure system/user prompts, and reduce hallucinations and irrelevant answers.
• Experience with containerization and deployment (Docker; basic Kubernetes or equivalent is a plus) and CI/CD workflows for backend or ML/AI services.
• Strong debugging and observability mindset, comfortable using logs, traces, and metrics dashboards to diagnose issues in distributed or tool-heavy workflows.
• Good communication and documentation skills, comfortable explaining design choices and trade-offs to engineers, data scientists, and non-technical stakeholders.

Nice-to-Have (Plus)

• Exposure to security considerations for LLM systems (prompt injection, data leakage, safe tool design) and working with security/compliance teams.
• Deeper experience with Databricks ML/AI features (e.g., MLflow, Model Serving) or advanced Snowflake Cortex use cases (e.g., agent-style workflows or in-DB vector search at scale).
• Experience contributing to architecture discussions and mentoring junior engineers on AI/LLM topics.