Senior Full-Stack Engineer, Agentic AI Applications

About the RoleWe're seeking a Senior Full-Stack Engineer focusing on Backend Engineering with strong software engineering expertise to build next-generation enterprise SaaS applications powered by agentic AI and large language models. You'll work at the intersection of modern enterprise SaaS and cutting-edge AI, focusing primarily on robust backend systems while contributing to full-stack development. This role transforms financial back-office operations through scalable, intelligent solutions with emphasis on data-intensive architectures, API integrations, and AI model orchestration.Key ResponsibilitiesArchitect and implement scalable backend services using Python, Node.js (TypeScript), and/or GoLang, handling AI model interactions, multi-agent orchestration, and data processing.Develop and optimize RESTful and gRPC APIs for seamless communication between frontend, backend, AI models, and multi-agent systems.Design AI-native full-stack applications integrating LLMs using modern protocols (MCP, A2A) with backend-centric approach for efficient data flows.Build performant database queries, indexing strategies, and schema designs across SQL (MySQL), NoSQL (MongoDB Atlas), and data warehouses (Snowflake).Implement advanced search capabilities including Atlas text searches and embedding-based retrieval for AI-enhanced features.Design AI-native workflow management systems enabling complex agentic automation for financial operations.Collaborate with AI engineers to integrate and optimize model deployments, focusing on backend scalability and production performance.Implement and maintain CI/CD pipelines using Kubernetes and GPU resources.Ensure high performance, reliability, and security of AI-integrated backend features including real-time data processing.Contribute to frontend development as needed using React.js for AI-powered interfaces and visual workflow designers.QualificationsBachelor's or Master's in Computer Science, Engineering, or related field.5+ years full-stack development experience with strong backend focus using Node.js (TypeScript) and Python.Hands-on experience building backend-heavy applications integrating with LLMs (GPT models) or generative AI.Proficient with prompt engineering and LLM fine-tuning concepts.Strong understanding of Kubernetes microservices architecture, REST APIs, and gRPC.Proficiency in modern Python, JavaScript/TypeScript, and associated ecosystems.Experience with AWS cloud services, deploying and scaling AI/ML workloads.Solid foundation in system design, data modeling, and databases:RDBMS (MySQL): query optimization, indexing, transactionsNoSQL (MongoDB Atlas): schema design, aggregation pipelines, text searchData warehouses (Snowflake): performant querying, data modelingUnderstanding of AI/ML concepts, particularly agentic AI applications.Experience with multi-tenant SaaS architectures and enterprise system integrations.Familiarity with API management tools like Postman.Demonstrated experience in complex projects with cross-team collaboration using APIs, microservices, and agile methodologies.Must be currently authorized to work in the United States without employer sponsorship, as we are unable to sponsor or transfer visas for this position.Must be located in or within commuting distance of Santa Clara, CA to be considered.Preferred QualificationsExperience implementing AI-native architectures using MCP (Model Context Protocol) and A2A (Agent-to-Agent).Proficiency with MongoDB Atlas text searches and embedding-based search systems (vector databases).Experience with real-time data processing using AWS Kinesis or Kafka.