Senior AI Engineer

You are a high-impact Senior AI Engineer who specializes in LLMs, agents, and intelligent systems. Your role involves designing and deploying AI-native applications that extend beyond basic chatbot integrations to include multi-agent systems, tool-using copilots, and end-to-end AI pipelines that deliver significant value. Your responsibilities will encompass various aspects of Agentic AI Architecture, such as building agent workflows using LangGraph, LangChain, CrewAI, and integrating tool use, memory, and planning into autonomous systems. You will orchestrate interactions across multiple LLMs and backends like GPT, Claude, Gemini fallback. Additionally, you will leverage AI to enhance developer team velocity by incorporating code generation, testing, documentation writing, PR reviews, and integrating tools like Copilot, Claud Code, Cursor into the SDLC to drive the adoption of AI-augmented engineering practices. In the Multi-Cloud AI Ecosystem domain, you will deploy applications using Azure AI Foundry, OpenAI, AWS Bedrock, Sagemaker, Kendra, Anthropic Claude, Mistral, and open-weight models, optimizing for model quality, latency, and cost. You will design and build retrieval-augmented generation (RAG) pipelines using tools like Weaviate, Pinecone, Qdrant, Azure AI Search, Redis, and customize chunking, embedding, ranking, and query rewriting. Your role also involves building scalable backend APIs using Python (FastAPI), Node.js, containerizing and deploying agents via Docker/Kubernetes, and constructing internal MSP-style infrastructure for LLM endpoints and copilots. Collaborating with product and engineering teams to solve real business problems using AI, guiding implementation decisions, and mentoring others in AI-native architecture are essential aspects of your role. Defining KPIs and demonstrating value through impact-driven rollouts are crucial for success. To excel in this position, you should possess 7+ years of software engineering experience with expertise in Python, API design, and cloud infrastructure, along with 3+ years of hands-on experience with LLMs like OpenAI, Claude, Gemini. Proven experience with agent frameworks, tool use, memory, RAG, and prompt engineering is required. A working knowledge of Azure, AWS, and Google Cloud AI offerings, DevOps skills including Docker, CI/CD, observability, and strong communication and problem-solving mindset are essential. It would be advantageous to have experience in building AI copilots, agent networks, or backend AI orchestration systems, familiarity with secure deployment of LLMs, Responsible AI principles, prior work in developing tools or agent interfaces, and knowledge of pricing, throttling, and routing across LLM providers.,