Senior Java AI Engineer – Generative AI & RAG

J2B Global LLC

is seeking a Senior/Lead Java AI Engineer (Generative AI & RAG) for an

onsite

role in

Lake Mary, FL

on a

contract

basis. This position centers on building enterprise-grade GenAI and retrieval-augmented generation capabilities with strong technical leadership, security focus, and production readiness.

What you’ll build You will design and develop

enterprise Generative AI and RAG

solutions, integrating LLM capabilities into business workflows. The work covers everything from prompt and context design to vector search, evaluation, and production observability, with an emphasis on

accuracy, groundedness, latency, scalability, security, and cost .

Responsibilities

Design and develop enterprise-grade AI applications using

Java, Spring Boot ,

REST APIs , and

microservices .

Integrate

LLM and Generative AI

capabilities into enterprise applications and business workflows.

Develop and optimize

system prompts ,

few-shot prompts , reusable prompt templates,

structured outputs , and

context-management

strategies.

Integrate with

OpenAI APIs ,

Azure OpenAI ,

Azure AI services ,

Azure AI Foundry , and other frontier AI model APIs.

Design and implement

RAG solutions

using

embeddings ,

vector search , document retrieval, grounding, and citation patterns.

Evaluate and optimize models and prompts for

accuracy ,

groundedness ,

latency ,

scalability ,

security , and

cost .

Implement

AI security controls

to mitigate prompt injection, hallucinations, sensitive-data exposure, and unauthorized access.

Build production-ready

logging, tracing, monitoring, observability , fallback, and error-handling mechanisms.

Lead architecture discussions, code reviews, technical troubleshooting, and production issue resolution.

Collaborate with business, product, architecture, and engineering stakeholders to move AI solutions from

proof of concept to production .

Mentor engineers and establish

reusable standards

for secure AI integration and application development.

Requirements

10+ years of enterprise software or application development experience.

Strong hands-on experience with

Java, Spring Boot, REST APIs, and microservices .

Hands-on experience delivering

LLM-based applications

and

production GenAI

solutions.

Strong knowledge of system prompts, few-shot prompting, prompt optimization, structured outputs, and context management.

Experience integrating

OpenAI APIs ,

Azure OpenAI ,

Azure AI services , or

Azure AI Foundry .

Experience with

embeddings ,

vector search , vector databases, retrieval, grounding, and document processing.

Ability to integrate and evaluate modern frontier AI models and model APIs.

Working experience with

Oracle ,

SQL , data-access layers, and enterprise persistence patterns.

Understanding of

AI security ,

data privacy , access control, prompt-injection mitigation, and responsible AI practices.

Working knowledge of

Git ,

CI/CD ,

Docker ,

Kubernetes , and cloud deployment.

Strong stakeholder communication, architecture, mentoring, and technical decision-making skills.

Technologies Java ,

Spring Boot ,

REST APIs ,

microservices ,

LLMs ,

prompt engineering ,

OpenAI APIs ,

Azure OpenAI ,

Azure AI services ,

Azure AI Foundry ,

embeddings ,

vector search ,

vector databases ,

Oracle ,

SQL ,

Git ,

CI/CD ,

Docker ,

Kubernetes ,

Azure DevOps ,

GitHub ,

Maven ,

Gradle ,

OpenAI ,

Azure AI

Preferred skills

Experience with AI agents, tool/function calling, orchestration frameworks, and structured model outputs.

Experience developing LLM evaluation frameworks and monitoring model quality, groundedness, latency, token usage, and cost.

Experience deploying AI-enabled microservices in regulated or large-scale enterprise environments.

Familiarity with Azure DevOps, GitHub, Maven or Gradle, and automated deployment pipelines.

Expected candidate profile

Approximately

60–70%

hands‑on engineering, with the ability to independently own solution design and delivery.

Ability to explain end-to-end

LLM or RAG architecture , including associated security controls.

Delivered at least one Generative AI use case from proof of concept toward production deployment.

Comfortable working onsite and collaborating with business, architecture, product, and engineering stakeholders.

Strong analytical, troubleshooting, communication, and mentoring capabilities.

Location and eligibility

Location:

Lake Mary, FL (onsite)

Visa:

US Citizen, Green Card, or GC-EAD

#J-18808-Ljbffr