American IT SystemsAbout this role
Summary: Design and deploy production-grade microservices in Java to integrate large language models and generative AI capabilities into enterprise systems. The role involves architecting RESTful APIs, implementing RAG, and optimizing model performance while collaborating with data scientists to deliver scalable AI solutions.
Gen AI Engineer with Java & Microservices
Atlanta is rapidly emerging as a hub for artificial intelligence and enterprise technology, and we are seeking a talented Gen AI Engineer to join a forward-thinking team dedicated to building intelligent, scalable solutions. This role is perfect for a software engineer who combines deep expertise in Java and microservices architecture with a passion for large language models, generative AI, and the practical deployment of these cutting-edge technologies. You will be at the forefront of transforming complex business challenges into innovative, AI-powered products that drive real impact.
As a Gen AI Engineer in Atlanta, you will be responsible for designing and implementing robust, production-ready AI services that integrate seamlessly with existing enterprise systems. Our team values a collaborative, agile culture where engineers are encouraged to experiment, iterate, and own their work from concept to deployment. Your primary focus will be on bridging the gap between theoretical generative models and reliable, high-performance microservices, ensuring that our AI solutions are not only intelligent but also resilient, secure, and maintainable. This is an opportunity to shape the future of our platform and contribute to Atlanta's vibrant tech community.
You will play a key role in the entire lifecycle of AI feature development—from identifying opportunities for generative AI to improving user experience, to designing the APIs and services that make these features accessible. By joining our team, you will help establish best practices for integrating LLMs into microservice-based architectures, tackling challenges like prompt management, response streaming, cost optimization, and model evaluation. Your work will directly influence how our organization leverages generative capabilities to enhance productivity, automate complex workflows, and deliver personalized user experiences.
### Key Responsibilities
- Design, develop, and deploy production-grade microservices in Java (using frameworks like Spring Boot) that integrate with a variety of large language models and AI/ML platforms.
- Architect and implement RESTful APIs and event-driven communication patterns to expose generative AI capabilities to internal and external clients.
- Develop robust prompt engineering strategies, including prompt templating, chaining, and dynamic context management, to optimize model output for specific business use cases.
- Implement features such as Retrieval-Augmented Generation (RAG), integrating vector databases to provide grounded, context-aware responses from proprietary knowledge bases.
- Build resilient integration layers to handle model inference, including retry logic, timeouts, rate limiting, and fallback mechanisms to ensure high availability.
- Develop services for asynchronous processing and streaming responses, ensuring efficient handling of long-running inference tasks.
- Implement comprehensive monitoring, logging, and observability solutions (e.g., tracking token usage, latency, and model performance) to ensure the health of AI services.
- Collaborate closely with data scientists and ML engineers to convert experimental models into production-ready code, focusing on system architecture and performance optimization.
- Develop and execute unit, integration, and load tests for AI services, ensuring code quality and system reliability under pressure.
- Participate in the evaluation of new generative AI models, libraries, and tools, providing technical assessments and recommendations.
- Write technical documentation and contribute to the maintenance of our internal AI service frameworks and shared libraries.
- Stay current on the rapidly evolving Gen AI landscape, proactively suggesting improvements to our architecture and development practices.
### Required Qualifications
- Bachelor's degree in Computer Science, Software Engineering, or a related technical field (or equivalent practical experience).
- 5+ years of professional software development experience, with a strong emphasis on object-oriented programming and enterprise-level application development.
- Expert proficiency in Java, including advanced concepts like concurrency, functional programming patterns, and robust error handling.
- Deep hands-on experience building and deploying applications using microservices architecture, including service discovery, API gateways, and distributed tracing.
- Strong working knowledge of Spring Boot or a similar Java-based micro-service framework, including testing and configuration.
- Proven experience integrating with third-party AI/LLM APIs (e.g., OpenAI, Anthropic, or open-source models) within a server-side environment.
- Solid understanding of cloud platforms (AWS, GCP, or Azure) and experience with containerization (Docker) and orchestration (Kubernetes) is highly desirable.
- Proficiency with databases (SQL and NoSQL) and practical experience using vector databases (e.g., Pinecone, Weaviate, pgvector) for semantic search.
- Working knowledge of observability tools and practices, including logging frameworks, metrics collection, and monitoring dashboards.
- Excellent problem-solving, debugging, and analytical skills with a proactive and self-directed work ethic.
- Strong communication skills with the ability to collaborate effectively in a team environment and translate complex technical concepts to non-technical stakeholders.
- Passion for learning new technologies, particularly in the field of generative AI and machine learning engineering.