DeveloperJobs.io
← Back to all jobs

Job Description

Lead GenAI-focused architecture and hands-on delivery of secure, production-ready capabilities integrated into Java and Spring Boot microservices.

Responsibilities

  • Design and govern scalable, secure architectures that embed LLMs and foundation models into core business platforms and microservices backends.
  • Architect and standardize microservices using Java 17+ / Java 21, Spring Boot 3.x, and reactive patterns via Spring WebFlux, targeting low latency and high throughput with distributed caches and databases.
  • Design and implement robust RAG pipelines, semantic caching, vector search indexing, and agent orchestration patterns using frameworks such as LangChain4j, Spring AI, Semantic Kernel, or custom orchestrators.
  • Set architectural guardrails for model security, including prompt injection defenses, PII masking, DLP, token cost optimization, and model evaluation with observability.
  • Drive event-driven integration with Apache Kafka and cloud-native deployments across AWS/GCP/Azure.
  • Use Docker and Kubernetes with Helm for container orchestration and operational deployment of AI-enabled services.
  • Own code quality, technical roadmaps, and architecture review board (ARB) approvals; guide engineering leads and delivery teams through complex integration work.
  • Lead technical implementation of Java-based microservices integrating GenAI capabilities, intelligent automation pipelines, and enterprise data connectors.
  • Build and maintain RAG functionality including fine-tuned retrieval algorithms, semantic vector lookups, and structured prompt templates with robust validation.
  • Write and review production-grade, high-performance code in Java 17+ and Spring Boot, including REST/GraphQL endpoints, Kafka consumers/producers, and asynchronous event processing.
  • Increase test quality through high code coverage with JUnit 5, Mockito, and TestContainers; implement automated testing for GenAI outputs (groundedness, hallucination detection, and prompt regression testing).
  • Perform PR code reviews, mentor engineers on best practices, help with developer productivity workflows (e.g., GitHub Copilot, Claude Code), manage sprint deliverables, and resolve technical blockers.
  • Partner with SRE/DevOps to monitor service health, token usage, latency bottlenecks, and logging/observability with tools like Splunk, Grafana, and OpenTelemetry.

Requirements

  • 12.00 years of experience.
  • Extensive enterprise experience with Java 17+, Spring Boot 3.x, Spring Cloud, and Spring Data.
  • Hands-on experience integrating with LLM APIs such as OpenAI, Anthropic Claude, Azure OpenAI, Bedrock, or open-source models using Java-native frameworks like Spring AI or LangChain4j or REST/gRPC wrappers.
  • Deep knowledge of embeddings, chunking strategies, hybrid search, and vector databases including pgvector, OpenSearch, Pinecone, Milvus, or Qdrant.
  • Proven expertise in distributed system patterns including SAGA, CQRS, Circuit Breaker, and Event Sourcing, plus real-time streaming architecture with Apache Kafka.
  • Hands-on proficiency with PostgreSQL, Oracle, MongoDB, and Redis.
  • Solid background in cloud architectures (AWS/GCP), container platforms (Docker, Kubernetes), and CI/CD automation pipelines.
  • Practical experience using Spring AI, LangChain4j, or Python AI service wrappers to build agentic and RAG workflows.
  • Working familiarity with vector search engines and extensions such as pgvector, OpenSearch, ChromaDB, or Elasticsearch.
  • Practical experience with PostgreSQL or Oracle alongside message brokers like Apache Kafka or RabbitMQ.
  • Strong foundation in unit, integration, and contract testing with JUnit and TestContainers, Git workflows, and CI/CD pipelines including Jenkins and GitHub Actions.
  • Demonstrated success leading a team of 4–8 engineers, including code reviews, estimating technical stories, and collaborating with distributed teams.
  • Preferred experience (years listed in data): AMS for Apache Kafka (10), Spring WebFlux (10), Springboot Microservices (10), MongoDB (10), Grafana (10), Spring Cloud (10), Prompt Engineering (3), GenAI Architect (3), and Java (17+) (5).

Technologies

  • Backend & Java: Java 17+, Java 21, Spring Boot 3.x, Spring Cloud, Spring Data, Spring WebFlux
  • GenAI & RAG: Spring AI, LangChain4j, Semantic Kernel, RAG, LLM, token cost optimization, PII masking, DLP
  • Model providers: OpenAI, Anthropic Claude, Azure OpenAI, Bedrock
  • Vector & search: pgvector, OpenSearch, Pinecone, Milvus, Qdrant, ChromaDB, Elasticsearch, vector databases
  • APIs & integration: REST, GraphQL, REST/gRPC, Kafka consumers/producers
  • Streaming & patterns: Apache Kafka, SAGA, CQRS, Circuit Breaker, Event Sourcing
  • Datastores & caching: PostgreSQL, Oracle, MongoDB, Redis, RabbitMQ
  • Cloud, containers, DevOps: Docker, Kubernetes, Helm, AWS, GCP, Azure, Jenkins, GitHub Actions
  • Testing & observability: JUnit 5, Mockito, TestContainers, Splunk, Grafana, OpenTelemetry
  • Developer tools: GitHub Copilot, Claude Code
  • Frontend mentioned: Angular, Spring Cloud Data flow

Benefits

  • 401(k)

Location: Austin, TX (hybrid)

Compensation: USD 45 - 50 per hourly

Similar Jobs