About this role
- Design, develop, and maintain Generative AI applications using Python and modern AI frameworks.
- Develop AI-powered enterprise solutions leveraging Large Language Models (LLMs), including OpenAI, Azure OpenAI, Amazon Bedrock, or similar AI platforms.
- Build Retrieval-Augmented Generation (RAG) solutions using enterprise data sources, vector databases, embeddings, and knowledge retrieval techniques.
- Design and develop Agentic AI workflows that enable autonomous task execution, reasoning, planning, and tool utilization.
- Develop AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar agent orchestration technologies.
- Perform prompt engineering and optimize LLM responses for accuracy, reliability, and business use cases.
- Integrate Generative AI capabilities into existing enterprise applications through REST APIs and backend services.
- Develop AI-powered chatbots, copilots, and intelligent automation solutions.
- Support integration of AI models with business systems, databases, and enterprise platforms.
- Design and implement API services using Python frameworks such as FastAPI or Flask.
- Develop data processing pipelines for AI applications, including data preparation, transformation, and indexing.
- Work with relational databases and vector databases to support AI knowledge management solutions.
- Support AI model evaluation, testing, monitoring, and continuous improvement.
- Assist with deployment and operation of AI applications in cloud environments.
- Participate in MLOps/LLMOps activities including CI/CD automation, model lifecycle management, and application monitoring.
- Collaborate with application developers, DevOps engineers, and business teams to deliver AI-driven solutions.
- Troubleshoot application issues and improve system performance and reliability.
- Document AI solutions, architecture, development processes, and operational procedures.
- Participate in Agile/Scrum ceremonies, sprint planning, and technical discussions.
- Bachelor's degree in Computer Science, Engineering, Data Science, or related field, or equivalent professional experience.
- Working knowledge of Python programming language.
- Understanding of Generative AI concepts, Large Language Models (LLMs), and AI application development.
- Experience or academic/project exposure with LLM-based application development.
- Understanding of Retrieval-Augmented Generation (RAG) architecture and AI knowledge retrieval concepts.
- Familiarity with prompt engineering techniques and LLM response optimization.
- Basic understanding of AI Agent concepts, including workflow automation, reasoning, and tool integration.
- Experience with REST API development and integration.
- Understanding of database concepts including SQL, data modeling, and data processing.
- Familiarity with cloud platforms such as AWS, Azure, or Google Cloud.
- Exposure to AI/ML frameworks and libraries such as LangChain, PyTorch, TensorFlow, or similar technologies.
- Basic knowledge of software development practices including Git, version control, and code reviews.
- Understanding of DevOps concepts including CI/CD pipelines and containerization (Docker preferred).
- Experience working with Linux environments.
- Strong problem-solving skills and ability to learn emerging technologies quickly.
- Excellent verbal and written communication skills.
Performance Expectations
- Develop and deploy enterprise Generative AI applications that improve business productivity.
- Build reliable AI Agent workflows capable of automating business processes.
- Design effective RAG solutions using enterprise knowledge sources.
- Improve LLM application accuracy through prompt engineering and evaluation.
- Create scalable AI application architectures and reusable AI components.
- Collaborate effectively with business users and technical teams to deliver AI solutions.
- Continuously learn and apply emerging AI technologies to enterprise use cases.
Preferred Qualifications
- Experience developing enterprise Generative AI applications or AI automation solutions.
- Hands-on experience with Agentic AI frameworks such as LangGraph, AutoGen, CrewAI, or similar technologies.
- Experience with cloud AI services such as:
-Amazon Bedrock
-Azure OpenAI Service
-AWS SageMaker
-Azure AI Studio
- Experience with vector databases such as:
-FAISS
-ChromaDB
-Pinecone
-OpenSearch Vector Engine
- Experience building AI-powered chatbots, copilots, or intelligent assistants.
- Knowledge of Java/Spring Boot enterprise application development.
- Experience with enterprise system integration and application operations.
- English-Korean bilingual communication skills.
All your information will be kept confidential according to EEO guidelines.