Senior Python Developer (Cloud / Generative AI) - Hybrid, Jacksonville, FL

Senior Python Developer (Cloud / Generative AI)
Location: Jacksonville, FL (Hybrid, onsite 2-3 days per week)
Type: Contract, through March 2027 (40 hrs/week)
Employment: W2 only.

About the Role
A large healthcare organization is seeking a Senior Python Developer to lead the architecture, development, and scaling of its next-generation AI orchestration platform. You will bridge cutting-edge GenAI capabilities and enterprise infrastructure, building advanced RAG pipelines, production-grade AI agents, MCP integrations, and multi-agent collaboration systems across a hybrid on-prem and AWS environment.

What You'll Do

• Architect, deploy, and scale GenAI services, vector databases, and model gateways across on-prem Red Hat OpenShift and AWS (EKS, Bedrock, EC2)
• Design and optimize enterprise RAG pipelines using hybrid search (vector + lexical) and cross-encoder reranking to reduce context noise, optimize token usage, and minimize hallucinations
• Build, deploy, and monitor production AI agents capable of autonomous planning, tool use, multi-step reasoning, and self-correction
• Architect scalable LLM integrations with enterprise data sources using the Model Context Protocol (MCP)
• Design and implement Agent-to-Agent (A2A) systems where specialized agents communicate, delegate tasks, and synchronize state
• Build secure, high-throughput, fault-tolerant Java/Spring Boot microservices to serve GenAI features and data orchestration

Required Qualifications

• 5+ years of professional experience in technical design and coding
• Expert-level Python for AI/ML, asynchronous programming, and data engineering
• Deep experience building distributed microservices with Java and Spring Boot (Spring Web, Spring Security, Spring Data)
• Hands-on experience deploying and troubleshooting containerized applications in on-prem Red Hat OpenShift, including security contexts, routes, and cluster resources
• Strong AWS expertise, including IAM, VPC, Bedrock, EKS, and RDS
• Practical experience with GenAI frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, LangChain4j, or Spring AI
• Experience with vector databases (Pinecone, Qdrant, Milvus, pgvector) and reranking tools (Cohere Rerank, BGE, or open-source cross-encoders)
• Solid understanding of MCP or experience building API abstraction layers for LLM tool use
• Familiarity with LLM evaluation frameworks, CI/CD targeting OpenShift/AWS, and observability tools such as Prometheus, Grafana, OpenTelemetry, or LangSmith
• Bachelor's degree in a related field or equivalent work experience

Preferred Qualifications

• Experience configuring on-prem OpenShift clusters with GPU acceleration (NVIDIA GPU Operator) for local LLM or embedding model hosting
• Red Hat Certified Specialist in OpenShift, AWS Certified Solutions Architect, or AWS Machine Learning Specialty certification
• Open-source contributions to GenAI projects, MCP servers, or multi-agent tools

Welcome to ConsultNet, a premier national provider of technology talent and solutions. Our expertise spans across project services, contract-to-hire, direct search, and managed services onshore, nearshore, and hybrid. For over 25 years, we have connected thousands of consultants with meaningful roles through a personal, communication-driven approach, partnering with a diverse client base to build high-performing teams and create lasting impact. Our comprehensive service offerings cover a wide range of technology and engineering positions across key markets nationwide. Learn more at www.consultnet.com .

We champion equality and inclusivity, proudly supporting an Equal Opportunity Employer policy. We welcome applicants regardless of Race, Color, Religion, Sex, Sexual Orientation, Gender Identity, National Origin, Age, Genetic Information, Disability, Protected Veteran Status, or any other status protected by law.