Information Technology USA - USA Developer

Full-Stack Generative AI Developer~PLEASANTON, CA~Seeking talented Full-Stack Generative AI Developer who will design, implement, and maintain cutting-edge AI-powered applications and services. In this role, developer will bridge the gap between advanced generative AI models and user-facing applications, creating intuitive interfaces for complex AI capabilities while ensuring robust, scalable, and efficient backend systems.Key ResponsibilitiesAI DevelopmentDesign and implement generative AI features leveraging models like GPT-5, Llama, or other foundational modelsFine-tune and optimize AI models for specific use cases and domains (optional, good to have)Create prompt engineering frameworks and templates to ensure consistent AI behaviorDevelop retrieval-augmented generation (RAG) systems that combine vector databases with LLMsWorking knowledge of LLM evaluation and observability platformsFrontend Development (Basic Exposure)Build responsive, accessible web interfaces for AI-powered applications using modern frameworks (React, Vue, Angular, MUI)Design intuitive UIs that make complex AI capabilities understandable and usableImplement real-time features for AI interactions (streaming responses, progressive rendering)Develop visualization components for AI outputs and confidence metricsBackend DevelopmentCreate robust APIs on python and similar framework and services to interface with AI models and external servicesDesign scalable architectures that can handle high-throughput AI inferenceImplement efficient data processing pipelines for AI training and inferenceIntegrate with vector databases, document stores, and other AI-specific infrastructureDevOps & MLOpsSet up CI/CD pipelines for AI application deploymentImplement monitoring, logging, and alerting for AI systemsOptimize infrastructure for cost-effective AI deploymentRequired Skills & ExperienceTechnical Skills3+ years of full-stack development experience (JavaScript/TypeScript, Python(must))1+ years working with AI/ML technologies, particularly generative AIExperience with at least one major LLM framework (LangChain, Langgraph)Proficiency with vector databases (Pinecone, Mongo, FAISS, etc.)