> Markdown version of [/jobs/ext/3735199-agentic-ai-engineer-llm-rag-python-hybrid](https://www.wearedevelopers.com/jobs/ext/3735199-agentic-ai-engineer-llm-rag-python-hybrid). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Agentic AI Engineer (LLM / RAG / Python) - Hybrid

- **Company:** Usg Inc.
- **Location:** Almond, NY, United States
- **Experience:** Experienced
- **Contract:** Contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Audit Trail, Microsoft Azure, Cloud Computing, Databases, Continuous Integration, Information Engineering, Python (Programming Language), OpenAI, Search Technologies, Software Engineering, Enterprise Search, Data Logging, Google Cloud, Enterprise Software Applications, Cloud Platform System, Data Ingestion, LangChain, Retrieval-Augmented Generation, Large Language Models, Snowflake, Prompt Engineering, Apache Spark, Generative AI, Backend, Agentic-AI, AI Platforms, Pyspark, CrewAI, AutoGen, Data Management, Artificial Intelligence Governance, Model Context Protocol, Databricks
- **Published:** October 14, 2026
- **Apply:** https://www.dice.com/job-detail/a77ce3b0-c035-44da-a74e-2779fb405a7a

## About the Role

* 2+ years of hands-on AI engineering experience building LLM, Generative AI, or Agentic AI solutions
 * 2+ years of strong hands-on experience with Agentic AI, LLMs, prompt engineering, and RAG
 * 2+ years of production development with Python, APIs, cloud platforms, and enterprise security practices
 * Delivered at least one complete production AI solution covering retrieval, tool execution, evaluation, deployment, and monitoring
 * Solid data engineering experience: ingestion, transformation, management, and delivery
 * Cloud experience on AWS, Azure, or Google Cloud Platform

Preferred Qualifications

 * Agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or Strands
 * AWS Bedrock, Azure AI Foundry/OpenAI, Anthropic, OpenAI, or similar enterprise AI platforms
 * Knowledge of Model Context Protocol (MCP)
 * Vector databases and enterprise search platforms
 * LLM/agent evaluation, tracing, and observability experience
 * AI guardrails, prompt-injection protection, audit logging, and Responsible AI practices
 * Databricks, Spark/PySpark, Snowflake, or similar data platforms
 * Strong software engineering, CI/CD, and cloud-native development background
 * Banking or financial services experience

## Description

We're looking for a hands-on Agentic AI Engineer to design, build, and deploy production-grade AI agents, LLM-powered applications, RAG solutions, and AI-enabled workflows for a major financial services client. Agentic AI and AI engineering are the core of this role. We want someone who has taken AI solutions beyond prototypes and into production, backed by a solid data engineering foundation., * Design, develop, and deploy production-grade Agentic AI and LLM-based solutions

 * Build AI agents that handle reasoning, retrieval, tool invocation, and multi-step workflows
 * Design and implement RAG solutions using enterprise data and knowledge sources
 * Develop prompt strategies, reusable templates, and context-management approaches
 * Build backend AI services and APIs in Python
 * Integrate LLMs and agents with enterprise applications, APIs, databases, and external tools, with proper authentication, authorization, and security controls
 * Develop retrieval pipelines covering document processing, embeddings, vector search, and contextual retrieval
 * Implement evaluation frameworks for retrieval quality, response quality, and agent behavior
 * Deploy to cloud environments and support production operations, including monitoring, logging, tracing, alerting, and observability
 * Troubleshoot production AI systems and improve accuracy, reliability, and latency
 * Build and maintain the data ingestion and transformation pipelines AI applications depend on
 * Collaborate with data engineers, data scientists, software engineers, architects, security teams, and business stakeholders
 * Rapidly build POCs/MVPs that can evolve into secure, scalable production solutions