Description:

Siemens Healthineers is hiring a Senior AI Engineer for its core HTML5 framework and platform provider group in Bangalore. Operating entirely onsite within an R&D capacity, this role functions at the intersection of system architecture, consulting, and full-stack AI implementation. Instead of training baseline convolutional networks, you will focus heavily on building advanced Agentic AI systems, Retrieval-Augmented Generation (RAG) frameworks, and intelligent developer tools designed to automate manual enterprise workflows. You will design vendor-agnostic AI capabilities, embed context-aware assistants natively into internal SDKs, optimize LLM inference tokens, and collaborate with frontend architects to engineer next-generation, AI-driven developer experiences.

Key Technologies:

LLMs (GPT, Claude, Gemini), Python, AI Frameworks (LangChain, LangGraph, Semantic Kernel, CrewAI, AutoGen), RAG Architecture, Vector Databases, Semantic Search, Agentic Workflows, Prompt Engineering, Model Context Protocol (MCP), Tool-Calling Architectures, Cloud Platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI), REST APIs, Microservices, System Design

Requirements:

• 4 to 7 years of professional software engineering experience, with a proven and verifiable track record building AI-powered features and production-ready automation solutions.
• Advanced development expertise integrating proprietary and open-source Large Language Models (such as GPT-4, Claude, and Gemini) utilizing modern orchestration layers like LangChain, LangGraph, CrewAI, AutoGen, or Microsoft Semantic Kernel.
• Practical implementation experience building end-to-end RAG (Retrieval-Augmented Generation) loops, integrating text embeddings, managing vector databases, and optimizing semantic search query logic.
• Deep understanding of multi-agent orchestration, complex workflow routing, precision prompt engineering, and multi-step autonomous tool use execution.
• Strong capability to design scalable system architectures, deploy secure microservices via REST APIs, and optimize AI platforms for token-cost reduction, response latency, and high reliability.

Preferred Skills:

• Direct experience developing autonomous AI co-pilots, specialized developer SDKs, or internal platform tools.
• Practical usage of enterprise cloud environments, including Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Exposure to the Model Context Protocol (MCP), advanced function calling, and structured code-generation workflows.
• Baseline structural familiarity navigating frontend development ecosystems (HTML5, JavaScript, TypeScript, Angular, or React) to smoothly integrate AI endpoints into client views.