Lead Generative AI Software Engineer

New Today

We are looking for a talented Lead Generative AI Software Engineer to join our innovative development team. In this exciting role, you will have the opportunity to architect, develop, and implement cutting-edge AI-powered solutions that redefine customer interactions with our products. Your primary responsibilities will include: Designing and developing enterprise-scale generative AI applications using .NET Core, C#, Python, and React, ensuring high levels of security, performance, and cost-effectiveness. Architecting sophisticated Retrieval-Augmented Generation (RAG) systems leveraging vector databases and hybrid search strategies. Building and integrating features powered by Large Language Models (LLMs) utilizing frameworks like LangChain, Semantic Kernel, and custom orchestration solutions. Creating responsive AI-driven user interfaces using React, TypeScript, and modern front-end best practices, effectively communicating AI capabilities and limitations to users. Developing robust APIs and microservices that expose AI capabilities while implementing thorough governance, monitoring, and safety measures. Leading the evaluation and selection of AI models, balancing performance, cost, and business needs. Implementing containerized AI applications using Docker and Kubernetes, focusing on resource management for GPU workloads. Establishing AI governance practices that include bias detection, content safety, prompt injection prevention, and ensuring compliance with requirements. Mentoring team members in both traditional software engineering and emerging AI practices. Collaborating with product managers and stakeholders to translate business needs into innovative AI solutions. Monitoring AI system performance, implementing cost optimization strategies, and ensuring reliable production operations. Staying informed about the rapidly evolving generative AI landscape through research, experimentation, and engagement with the community. Key Requirements: 5+ years of experience in full-stack development, with expertise in .NET/C# and strong proficiency in Python. 2+ years of hands-on experience in building production applications with LLMs (such as GPT-4, Claude, Gemini, or open-source models). Proven experience implementing RAG systems with vector databases (e.g., Pinecone, Weaviate, Azure AI Search). Strong proficiency in AI/ML frameworks including Hugging Face Transformers, LangChain, LlamaIndex, or similar. Experience with prompt engineering, model evaluation, and optimization techniques for LLMs. Please note that applicants may be required to appear onsite at a Wolters Kluwer office as part of the recruitment process. Compensation: Target salary range: $114,750 - $160,450.
Location:
Austin, TX, United States
Category:
Computer And Mathematical Occupations

We found some similar jobs based on your search