Role: Lead AI Engineer
Location: Lake Mary, FL
Duration: 6 months contract
Rate: $75/hr on C2C
Role Overview
We are seeking experienced Senior / Lead AI Engineers to design, build, and productionize enterprise Generative AI solutions. This onsite role combines strong Java and Spring Boot engineering with hands-on expertise in LLMs, prompt engineering, OpenAI and Azure AI integration, RAG, AI security, and model evaluation. The engineer will collaborate directly with business, architecture, product, and engineering stakeholders in Lake Mary.
Key Responsibilities
Design and develop enterprise-grade AI-enabled applications using Java, Spring Boot, REST APIs, and microservices.
Build and integrate LLM and Generative AI capabilities into business applications and workflows.
Develop and optimize system prompts, structured prompts, few-shot prompts, reusable prompt templates, and context-management strategies.
Integrate applications with OpenAI APIs, Azure OpenAI, Azure AI services, and other frontier AI models.
Design and implement RAG solutions using embeddings, vector search, document retrieval, grounding, and citation patterns.
Evaluate models and prompts for accuracy, groundedness, latency, scalability, security, and cost.
Implement safeguards for prompt injection, sensitive-data exposure, hallucination, authentication, authorization, and responsible AI usage.
Create production-grade logging, tracing, observability, model-response monitoring, fallback, and error-handling mechanisms.
Lead architecture discussions, code reviews, technical troubleshooting, and production issue resolution.
Partner with onsite stakeholders to refine use cases, communicate trade-offs, and move solutions from proof of concept to production.
Mentor engineers and establish reusable standards for AI integration and secure application development.
Required Technical Skills
Skill Area
Requirement
Overall Experience
10+ years in enterprise software or application development.
Generative AI
Hands-on delivery experience with LLM-based applications and production GenAI use cases.
Prompt Engineering
Strong knowledge of system prompts, few-shot prompting, prompt optimization, context management, and structured outputs.
Java / Spring
Strong hands-on experience with Java, Spring Boot, REST APIs, and microservices.
OpenAI / Azure AI
Experience integrating OpenAI APIs, Azure OpenAI, Azure AI services, or Azure AI Foundry.
RAG
Experience with embeddings, vector search or vector databases, retrieval, grounding, and document processing.
Frontier Models
Ability to integrate and evaluate modern frontier AI models and model APIs.
Oracle
Working experience with Oracle, SQL, data-access layers, and enterprise persistence patterns.
Security
Understanding of AI security, privacy, access control, prompt-injection mitigation, and responsible AI practices.
DevOps
Working knowledge of Git, CI/CD, Docker, Kubernetes, and cloud deployment.
Leadership
Strong stakeholder communication, architecture, mentoring, and technical decision-making skills.
Preferred Skills
Experience with AI agents, tool/function calling, orchestration frameworks, and structured model outputs.
Experience defining LLM evaluation frameworks and monitoring 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.
Can clearly explain an end-to-end LLM or RAG architecture and associated security controls.
Has moved at least one GenAI use case from proof of concept toward production deployment.
Comfortable working onsite with business, architecture, product, and engineering stakeholders.
Strong analytical, troubleshooting, communication, and mentoring capabilities.
