Generative AI & LLM Systems Engineer

This profile demonstrates extensive expertise in Generative AI and LLM Systems, including advanced techniques like RAG, prompt engineering, embedding pipelines, context management, model fine-tuning, AI evaluation, and hallucination mitigation. The individual is proficient with leading AI frameworks such as LangChain, LlamaIndex, LangGraph, and Hugging Face Transformers, and capable of building complex AI agent architectures, tool-augmented agents, multimodal AI systems, and managing conversation state and streaming inference. They possess strong backend and AI infrastructure skills using Python, Node.js, FastAPI, Express.js, NestJS, REST APIs, GraphQL, WebSockets, and microservices architecture for high-throughput inference services. Coupled with significant experience in cloud platforms (AWS, GCP Vertex AI, Azure OpenAI) and DevOps practices (Docker, Kubernetes, Terraform, CI/CD pipelines, serverless architecture), the profile also shows full-stack development capabilities with JavaScript, TypeScript, React, and Next.js for modern UI architectures and real-time applications. Furthermore, the profile has a solid understanding of diverse database systems, including PostgreSQL, MySQL, MongoDB, Redis, DynamoDB, Supabase, and vector databases (FAISS, Pinecone), with expertise in schema design, query optimization, and high-volume data processing. The individual is located in Chicago, IL, is open to remote work, but not willing to relocate.