Sr. Java Developer with Agentic AI, Kafka and LLM -Dallas, TX/NJ/Charlotte, NC

Key Responsibilities

• Enterprise Integration & Architecture: Design, build, and maintain production-ready microservices using Java and Spring Boot, with high-performance event-driven pipelines powered by Apache Kafka.
• Agentic AI & Knowledge Architecture: Build multi-agent workflows and complex orchestration pipelines using Lang Graph and Python. Model domain expertise using Knowledge Graphs to ground AI outputs in structured enterprise data.
• ADLC Transformation: Champion and operationalize AI-Driven Software Development Life Cycle (ADLC) frameworks to accelerate engineering throughput, maintain high code quality, and automate automated testing/deployment loops.
• Hands-on AI Tooling: Daily hands-on development leveraging AI coding agents and including in any one of the LLMs - Claude, Devin, and Antigravity CLI to automate complex code bases and workflow automation.
• CoE Enablement & Standards: Establish best practices, architecture patterns, and governance frameworks for integrating GenAI and Agentic systems with existing core backend services across the organization.

Core Software Engineering (Must-Have)

• Java & Spring Boot: Deep expertise in Java (12+ preferred), Spring Boot, Spring Cloud, RESTful APIs, and microservices design patterns.
• Event-Driven Architecture: Strong hands-on experience with Apache Kafka (producers, consumers, stream processing, topic architecture, and fault tolerance).
• Enterprise Delivery: Solid track record of deploying resilient, high-scale applications into production environments.

AI & Agentic Capabilities

• Python Proficiency: Strong functional programming capability in Python for AI framework integration.
• Agentic Frameworks: Hands-on experience building cognitive state machines or multi-agent systems using LangGraph (or similar orchestration frameworks like LangChain/AutoGPT).
• Knowledge Graphs: Experience with graph databases (e.g., Neo4j, Amazon Neptune, NetworkX) or semantic tech (RDF, SPARQL, Cypher) to represent contextual enterprise knowledge.
• Modern AI Engineering Tools: Deep hands-on experience using Claude (Claude 3.5 Sonnet / API workflows), Devin, or AntiGravity CLI for code generation, architectural refactoring, and automated development tasks.

Process & Frameworks

• ADLC Exposure: Comprehensive understanding of AI-Driven Development Life Cycles moving beyond basic prompt engineering into automated task breakdown, AI-assisted code reviews, automated refactoring, and continuous integration.

Nice to Have

• Experience with Vector Databases (Pinecone, Qdrant, Milvus) and hybrid search implementations (Graph + Vector / GraphRAG).
• Exposure to cloud-native deployments (AWS, Azure, or Google Cloud Platform) using Kubernetes and Terraform.
• Familiarity with evaluation frameworks for LLMs and agentic systems (e.g., Ragas, TruLens).