Ai Fullstack developer

Job description

**Role Overview:** Join our AI Engineering Team to build and scale agentic AI solutions, taking systems from concept to production-grade, enterprise-ready platforms. This role demands deep hands-on expertise across frontend, backend, AI integration, and DevOps, with strong ownership of system design, deployment, and operational excellence. Close collaboration with ML engineers, business owners, and product teams is essential to deliver robust, scalable AI-powered applications. **Key Responsibilities:** - Design and build end-to-end AI-powered applications using modern frontend/backend frameworks. - Integrate LLM and agentic AI components into user-facing and system-facing workflows. - Develop APIs/services supporting agent orchestration, tool calling, and workflow execution. - Build intuitive UIs for AI-assisted workflows, human-in-the-loop (HITL) interactions, and monitoring. - Operationalize ML/agentic models into production with RAG pipelines, vector search, and AI inference layers. - Manage model lifecycle: versioning, configuration, evaluation hooks, rollout strategies. - Implement safeguards, validations, and fallback mechanisms for AI-driven workflows. - Own CI/CD pipelines, containerization, and deployment of AI applications. - Ensure performance, scalability, security, and reliability; implement logging, monitoring, alerting, and cost visibility - Collaborate with platform/security teams on compliance and operational readiness. - Contribute to system and application architecture decisions for AI platforms. **Technical Skills Required:** - Strong Python fundamentals: decorators, lists/tuples/sets, multithreading vs. multiprocessing, generators, virtual environments. - Expert-level FastAPI: async vs. sync APIs, Pydantic, dependency injection, authentication, request validation/error handling, deployment (Uvicorn/Gunicorn, Docker), and rationale over Flask/Django. - AI/ML fundamentals: supervised/unsupervised learning, model training, fine-tuning, overfitting handling, performance optimization. - Libraries: NumPy, Pandas, scikit-learn; basic TensorFlow/PyTorch/Keras. - API integration of AI models; Git version control. - Practical exposure to prompt safety, cloud setup, cost optimization, and HITL workflows.