AI Full-stack Engineer

Job description Stop applying to jobs. Start your life's work At Quantum Gandiva AI, we're not just another startup. We are a deep-research AI lab based in Visakhapatnam, and we're building the Autonomy Stack for self-improving AI. We believe in practical, reproducible research, and we're looking for a foundational team member to build with us. We're building the next generation of AI agents and looking for an experienced Full Stack Engineer whohas hands-on experience of shipping web applications. Check the job description below: Position Title: AI Full-Stack Engineer Location: Visakhapatnam, Andhra Pradesh (locals preferred) Start Date: November 2025 (flexible for the right candidate) Company Overview: We are a dynamic startup developing an innovative AI-driven Anonymous Stack and building Self-Improved AI Systems. We warmly invite passionate individuals to join our collaborative team and contribute to meaningful projects in a supportive, growth-oriented environment. Role Overview: We are seeking a hands-on Full-Stack Engineer to build the core web experience and backend APIs that power agentic AI workflows—from scratch to a production-ready prototype. You will own end-to-end delivery across React/TypeScript (frontend) and Python/FastAPI (backend), with strong attention to reliability, security, performance, and clear telemetry. Key Responsibilities: Build user-facing web interfaces in React + TypeScript (state management, forms/validation, responsive UI) with clean, reusable components. Design and implement FastAPI services and REST endpoints (OpenAPI schemas, JSON contracts, pagination, error handling). Model data in PostgreSQL; implement caching with Redis; write efficient SQL; maintain migrations and seed scripts. Integrate with agent workflows (message threads, approvals/HITL, activity/audit views) via well-typed API contracts. Add observability (OpenTelemetry traces/metrics/logs), structured logging, and feature flags for safe rollouts. Implement auth (JWT/OAuth), RBAC/permissions, input validation, rate limiting, and basic security hardening (CORS/CSRF/XSS/SSR mitigations). Write tests (unit/integration/E2E via pytest/Playwright) and participate in CI/CD to keep releases fast, reliable, and secure. Partner with Applied AI, Data Engineering, and DevOps to ship end-to-end features and iterate from evaluation feedback. Document API contracts, architecture decisions, and runbooks to enable rapid onboarding and consistent delivery. Required Skills and Qualifications: Proficiency in React + TypeScript and modern tooling (Vite/Next.js), forms/validation (e.g., Zod), and component composition. Strong Python skills with FastAPI, async I/O, Pydantic models, and testing (pytest). Solid understanding of SQL/PostgreSQL, Redis caching, and data modeling for reliability and performance. Experience designing REST APIs (OpenAPI), handling auth/permissions, and integrating third-party services. Practical knowledge of observability (metrics/traces/logs) and performance tuning (p95/p99 latency, bundling, memoization). Ability to build fast, reliable, and secure implementations with clear error reporting and rollback strategies. Proficiency with AI coding tools like Claude for code generation and Cursor AI editor for rapid development. Well-versed in latest models and modules (e.g., for embeddings and integrations) and how to consume them safely via APIs. Add-on skill: Basic context engineering to structure frontend/backend payloads for efficient agent context windows. Experience Requirements: Years of professional experience are not mandatory; however, candidates must demonstrate a portfolio of shipped web applications and/or AI-enabled apps showing end-to-end ownership (frontend + backend), quality practices, and thoughtful API design.