About the Project :

We are seeking a Lead Python Engineer (Generative AI) to architect and develop an enterprise-grade, multi-tenant AI assistant that enhances internal company support operations. The platform will leverage Flask, MongoDB, and Googles Gemini AI to provide intelligent, context-aware answers to employees in real time. Development will be executed in a Dockerized environment with PyCharm as the primary IDE.

Key Responsibilities :

- Flask Backend Development : Design, implement, and maintain scalable RESTful APIs, authentication flows, and multi-tenant logic.

- AI Orchestration & Integration : Build and optimize the AI orchestration layer to manage query flows, integrate Gemini AI SDK, and implement intelligent tool-selection mechanisms.

- AI Tools & Services : Develop backend services (e.g., services.py) that enable the AI assistant to fetch real-time employee-specific data such as leave balances, expense statuses, and approvals.

- Database Engineering : Design and optimize MongoDB queries for user management, data ingestion, and low-latency lookups.

- Environment Management : Configure and troubleshoot Docker/Docker Compose environments. Maintain dependencies via requirements.txt.

- Debugging & Optimization : Leverage PyCharms advanced features for profiling, debugging, and code optimization across the stack.

- Collaboration & Best Practices : Enforce coding standards, participate in code reviews, and mentor team members on Python and AI-driven application development.

Required Skills :

- Expert-level Python development with hands-on experience in Flask.

- Strong knowledge of MongoDB or other NoSQL databases.

- Proficiency with Docker/Docker Compose in enterprise environments.

- Advanced debugging and troubleshooting skills using PyCharm or equivalent IDE.

- Proven ability to design scalable, modular, and maintainable systems.

Preferred Skills :

- Familiarity with Generative AI concepts such as RAG (Retrieval-Augmented Generation) and Tool-Calling.

- Experience in architecting or scaling multi-tenant SaaS applications.

- Exposure to enterprise-grade AI chatbots or conversational AI platforms.

- Working knowledge of cloud-based deployment (AWS, GCP, or Azure).