Senior Fullstack AI Engineer

Responsibilities

• Design, develop, and deploy end-to-end AI-powered applications using React, Python, FastAPI, and AWS services.
• Build responsive and scalable frontend applications using React and optionally Next.js, ensuring seamless user experiences for AI-driven workflows.
• Develop backend APIs and microservices using Python and FastAPI to support AI and business application requirements.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embedding generation, retrieval optimization, and response orchestration.
• Implement and integrate Model Context Protocol (MCP) servers and clients to enable secure communication between AI systems, tools, and enterprise applications.
• Build and maintain AI agent workflows leveraging Amazon Bedrock, foundation models, and agent orchestration frameworks.
• Integrate with LLM providers and Bedrock foundation models while implementing prompt engineering, tool calling, structured outputs, and reasoning workflows
• Design and implement vector database integrations and semantic search capabilities to support enterprise knowledge retrieval use cases.
• Develop real-time AI experiences using streaming APIs, Server-Sent Events (SSE), and Web Socket-based architectures
• Collaborate with product managers, architects, and business stakeholders to translate requirements into scalable AI solutions.
• Implement security, authentication, authorization, and observability best practices across AI applications and APIs.
• Participate in architecture reviews, code reviews, and technical design discussions while contributing to engineering best practices.

• 5+ years of software engineering experience with strong full‑stack development expertise.
• Experience with Next.js for server‑side rendering and modern web application development (preferred but not mandatory)
• Strong proficiency in Python and backend development using FastAPI.
• Experience designing and implementing Retrieval‑Augmented Generation (RAG) systems in production environments.
• Hands‑on experience with Model Context Protocol (MCP), including MCP clients, servers, tools, and integrations.
• Strong knowledge of Amazon Bedrock and foundation model integrations.
• Experience working with LLMs such as Claude, Llama, Amazon Nova, Mistral, OpenAI, or similar models
• Experience implementing vector databases and semantic search solutions using technologies such as Pinecone, Weaviate, Chroma, or FAISS.
• Strong understanding of prompt engineering, tool calling, agent orchestration, and AI application architectures
• Experience developing REST APIs, microservices, and event‑driven architectures.
• Familiarity with AWS services including Bedrock, Lambda, API Gateway, S3, DynamoDB, ECS/EKS, Cloud Watch, IAM, and Secrets Manager.
• Experience with Docker, containerized deployments, and CI/CD pipelines.
• Strong understanding of authentication and authorization mechanisms including JWT, OAuth, and OIDC.
• Excellent problem‑solving, communication, and collaboration skills.