Senior full-stack engineer with deep expertise in LLM backend and front-end development using React/Next.js. Design and deploy LLM-powered services, RAG systems, and build high-performance front-end applications. Must have 8+ years backend experience with Python and 5+ years frontend. Contract role remote in US.
Responsibilities
Design, build, and deploy LLM-powered services using Python, FastAPI/Flask, and modern microservices architectures.
Work with leading LLM providers and frameworks (e.g., OpenAI, Anthropic, LangChain, LlamaIndex).
Implement and productionize Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search.
Design multi-agent and context-aware AI systems, including experience with Model Context Protocol (MCP).
Develop prompt strategies and system-level orchestration for real-world, scalable AI use cases.
Own AI features end-to-end, from design and experimentation through production rollout and optimization.
Ensure robustness, security, observability, and performance of AI systems deployed at scale.
Build and maintain React-based applications using Next.js, optimized for performance, scalability, and SEO.
Implement SSR, SSG, and edge-rendered experiences to support enterprise use cases.
Deploy and manage applications on Vercel, leveraging CI/CD pipelines, serverless functions, and edge capabilities.
