AI Engineer

Kforce has a client in Houston, TX in search of an AI Engineer. Our client is seeking an Applied AI Engineer to join our growing Data & AI team. This role is ideal for an experienced software engineer with a deep understanding of generative AI technologies and a passion for building scalable, production-grade AI solutions. You will be responsible for designing, prototyping, and deploying GenAI-powered applications, while also contributing to our AI platform architecture across cloud environments such as Google Cloud Platform (GCP) and Microsoft Azure. Key Responsibilities:

• Translate business needs into robust, scalable GenAI technical solutions.
• Design, prototype, and implement LLM-driven applications using techniques such as RAG, prompt engineering, fine-tuning, and vector search.
• Develop APIs and reusable software components in Python to support GenAI applications.
• Leverage orchestration frameworks (e.g., LangChain, LlamaIndex, or LangGraph) to deliver dynamic and modular AI workflows.
• Collaborate with cross-functional teams to integrate AI capabilities into business applications.
• Deploy and monitor GenAI models and pipelines using cloud-native tools, Kubernetes, and serverless architectures.
• Continuously evaluate model and system performance, implementing improvements as needed.
• Create and maintain technical documentation and support materials for deployed solutions.
• Bachelor's or Master's degree in Computer Science, AI/ML, or a related field
• 5+ years of software development experience with strong Python skills
• 2-3+ years of hands-on experience building GenAI/LLM-based applications
• Experience developing multi-step agent workflows using LangGraph or similar orchestration frameworks
• Proficient in designing retrieval pipelines: document loaders, chunking strategies, embedding models, and vector database integration

• Retrieval-Augmented Generation (RAG)
• Embeddings and vector databases (e.g., FAISS, Pinecone, ChromaDB)
• Prompt engineering and fine-tuning
• LLM APIs (e.g., OpenAI, Claude, Gemini)
• Experience deploying cloud-native solutions using GCP and/or Azure
• Solid understanding of API design, microservices, and software architecture patterns
• Familiarity with version control systems (e.g., Git, Azure DevOps)
• Experience with Docker and Kubernetes
• Demonstrated ability to build and scale AI/ML solutions from proof-of-concept to production

• Experience with GenAI orchestration tools (e.g., LangChain, LlamaIndex)
• Familiarity with DevOps practices: Azure DevOps, YAML pipelines, Terraform
• Strong interpersonal and communication skills, with the ability to collaborate across teams and influence decision-making
• Self-starter with a proactive mindset and strong problem-solving abilities
• Ability to work both independently and in collaborative team environments
• Interest in leveraging AI tools to enhance productivity and solution delivery