Role Overview: Architect and lead the development of the application layer for enterprise GenAI solutions. Connect LLM backends to scalable frontends while managing API gateways and cloud deployments. Key Responsibilities Application Architecture: Design scalable microservices that handle LLM requests, streaming responses (Server-Sent Events), and context management. Cloud & DevOps: Oversee the deployment of AI applications on AWS, Azure, or GCP. Integrate CI/CD pipelines for AI software components. Frontend & Backend Integration: Ensure seamless, low-latency integration between modern frontends (React/Next.js) and Python/FastAPI backends running AI models. Required Skills & Qualifications • Tech Stack: Strong Python programming, familiarity with APIs (OpenAI, Anthropic), basic LangChain/LlamaIndex usage. • Qualifications: Bachelor’s in CS or related field; 3–4 years software or data engineering experience with demonstrated exposure to LLM APIs.