Java Technical Lead (Java 17+, Gen AI, LLM)

Our client, an IT Services and Consulting company, is looking for a Java Technical Lead (Java 17+, Gen AI, LLM) for their Austin, TX/Hybrid location.

Responsibilities:

• Enterprise GenAI Solution Architecture: Design and govern scalable, secure architectures embedding LLMs and foundation models into core business platforms and microservices backends.
• Modern Java & Microservices Ecosystems: Architect and standardize microservices utilizing Java 17+ / Java 21, Spring Boot 3.x, and reactive patterns (Spring WebFlux), ensuring low latency, high throughput, and seamless integration with distributed caches and databases.
• RAG & Agentic Workflows: Design and implement robust RAG pipelines, semantic caching, vector search indexing, and agent orchestration patterns (using frameworks like LangChain4j, Spring AI, Semantic Kernel, or custom orchestrators).
• AI Governance, Security & Guardrails: Establish architectural guardrails for model security, prompt injection defenses, PII masking, data loss prevention (DLP), token cost optimization, and model evaluation/observability.
• Distributed Scalability & Deployment: Champion event-driven integration using Apache Kafka, container orchestration via Docker and Kubernetes/Helm, and cloud-native AI deployments (AWS/GCP/Azure).
• Technical Governance & Mentorship: Drive code quality, technical roadmaps, architecture review board (ARB) approvals, and guide engineering leads and delivery teams through complex integration challenges.
• Hands-on Engineering & Delivery: Lead the technical implementation of Java-based microservices integrating GenAI capabilities, intelligent automation pipelines, and enterprise data connectors.
• RAG & Prompt Engineering Execution: Build and maintain RAG pipelines, fine-tune retrieval algorithms, implement semantic vector lookups, and design structured prompt templates with robust validation.
• Microservices Development: Write and review production-grade, high-performance code in Java 17+ and Spring Boot, implementing REST/GraphQL endpoints, Kafka consumers/producers, and asynchronous event processing.
• Testing & Quality Assurance: Drive high code coverage with JUnit 5, Mockito, and TestContainers; establish automated testing for GenAI outputs (groundedness, hallucination detection, prompt regression testing).
• Team Leadership & Sprint Governance: Conduct PR code reviews, mentor engineers on best practices (including developer productivity tools like GitHub Copilot/Claude Code), manage sprint deliverables, and resolve technical blockers.
• Production Operations: Partner with SRE/DevOps to monitor service health, token usage, latency bottlenecks, and logging/observability using tools like Splunk, Grafana, or OpenTelemetry.

Requirements:

• Deep enterprise engineering roots in modern Java (17+) and Spring Boot microservices. In this role, the selected candidate will define the architectural blueprint for integrating enterprise-grade Generative AI capabilities-including LLM orchestration, Retrieval-Augmented Generation (RAG), vector databases, and multi-agent workflows-into resilient, high-throughput microservices ecosystems.
• The successful candidate will partner with the business, AI/ML research, platform engineering, and delivery stakeholders to deliver secure, production-hardened AI solutions.
• Core Languages & Frameworks: Extensive enterprise experience in Java 17 or above, Spring Boot 3.x, Spring Cloud, and Spring Data.
• GenAI & LLM Tooling: Hands-on experience integrating with LLM APIs (OpenAI, Anthropic Claude, Azure OpenAI, Bedrock, or open-source models) using Java-native AI frameworks (e.g., Spring AI, LangChain4j) or REST/gRPC wrappers.
• RAG & Vector Stores: Deep understanding of embeddings, chunking strategies, hybrid search, and vector databases (e.g., pgvector, OpenSearch, Pinecone, Milvus, Qdrant).
• Microservices Architecture: Proven expertise in distributed system patterns (SAGA, CQRS, Circuit Breaker, Event Sourcing) and real-time streaming architectures using Apache Kafka.
• Databases: Hands-on proficiency with relational and NoSQL databases (PostgreSQL, Oracle, MongoDB, Redis).
• Cloud & DevOps: Solid background in cloud architectures (AWS/GCP), container platforms (Docker, Kubernetes), and CI/CD automation pipelines.
• We are seeking a hands-on Technical Lead specializing in Java 17+ and Spring Boot microservices with practical experience implementing Generative AI features. You will bridge architecture and execution, guiding a team of engineers in building, optimizing, and deploying AI-augmented microservices, fine-tuning RAG retrieval systems, and ensuring clean, resilient enterprise code.
• Programming & Core Stack: Strong proficiency in Java 17+, Spring Boot, and Microservices architecture.
• GenAI Frameworks & Integrations: Practical experience using Spring AI, LangChain4j, or Python AI service wrappers to interface with foundational models and build agentic/RAG workflows.
• Vector Databases & Search: Working familiarity with vector search extensions and engines (e.g., pgvector, OpenSearch, ChromaDB, or Elasticsearch).
• Data & Messaging: Practical experience with PostgreSQL or Oracle, alongside message brokers like Apache Kafka or RabbitMQ.
• Testing & Modern Engineering: Strong foundation in unit, integration, and contract testing (JUnit, TestContainers), Git workflows, and CI/CD pipelines (Jenkins, GitHub Actions).
• Leadership & Collaboration: Demonstrated success in leading a team of 4-8 engineers, conducting code reviews, estimating technical stories, and collaborating across distributed teams.
• Modern Java & Microservices Core: Extensive hands-on expertise in Java 17+, Spring Boot 3.x, REST/Reactive APIs, and distributed microservices architecture.
• Enterprise GenAI & LLM Integration: Practical experience with LLM orchestration, frameworks like Spring AI or LangChain4j, RAG pipelines, prompt engineering, and guardrails/security.
• Vector Databases & Data Ecosystem: Proficiency in semantic search tools and vector stores (e.g., pgvector, OpenSearch), alongside messaging queues (Apache Kafka) and enterprise databases (PostgreSQL/Oracle).
• Years of Experience: 12.00 Years of Experience

Why Should You Apply?

• Health Benefits
• Referral Program
• Excellent growth and advancement opportunities