AI / LLM Software Engineer - 100% remote - W2 only (no sponsorship)

100% REMOTE!We are seeking a Senior AI / LLM Engineer to design, develop, and deploy production-ready AI applications. This role focuses on building scalable LLM solutions, improving retrieval accuracy, integrating enterprise systems, and ensuring secure, reliable performance.Key ResponsibilitiesDesign and deploy LLM-powered applications and features.Build and optimize RAG pipelines, embeddings, vector databases, and data ingestion processes.Integrate LLM APIs and enterprise platforms into backend systems.Develop evaluation methods to improve AI accuracy, performance, and reliability.Implement secure data access, user permissions, monitoring, and audit capabilities.Lead technical design decisions and mentor other engineers.Required Qualifications5+ years of software engineering experience, including 2+ years working with LLMs or applied AI in production.Strong Python and backend development skills.Hands-on experience with RAG, vector databases, embeddings, and retrieval optimization.Experience building data ingestion and ETL pipelines.Proficiency integrating APIs, authentication systems, and event-driven applications.Experience with LLM frameworks, model evaluation, and production deployments.Knowledge of access controls, multi-user systems, and data security.Cloud experience, preferably AWS.Preferred QualificationsExperience with managed LLM services such as Amazon Bedrock.Familiarity with knowledge graphs and enterprise collaboration platforms.Experience with Docker, CI/CD, and MLOps practices.Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent experience.If you're passionate about building practical, scalable AI solutions and taking them from concept to production, we'd love to hear from you!