Senior Developer, Agentic AI

We are seeking a Senior Developer – Agentic AI with 7–10 years of experience in software development, including deep expertise in Large Language Models (LLMs), Generative AI, and Agentic AI systems. This role focuses on designing, building, and scaling AI-powered applications leveraging LLM orchestration frameworks, Retrieval-Augmented Generation (RAG), and cloud-native AI platforms such as Vertex AI / Gemini and OpenAI.

• Architect and develop advanced Agentic AI systems leveraging LLM orchestration frameworks such as LangChain, LangGraph, or equivalent agent frameworks.
• Design and implement scalable Retrieval-Augmented Generation (RAG) pipelines using vector databases and enterprise knowledge sources.
• Build and manage MCP (Model Context Protocol) servers to enable secure tool integration, contextual memory, and dynamic capability exposure for AI agents.
• Develop multi-agent workflows capable of reasoning, planning, tool usage, memory management, and autonomous task execution.
• Integrate enterprise systems and external tools into agent ecosystems via MCP-compliant services and APIs.
• Build AI-powered backend services using Python (FastAPI/Flask) that expose LLM-driven capabilities securely and at scale.
• Implement prompt engineering strategies, structured output handling, and tool-calling mechanisms for reliable agent execution.
• Design and deploy solutions using OpenAI, Gemini (Vertex AI), or equivalent LLM platforms.
• Implement observability, tracing, evaluation, and guardrails for production AI systems (e.g., LangSmith, Ragas, DeepEval).
• Optimize LLM inference performance for cost, latency, reliability, and scalability in enterprise environments.
• Collaborate with Product and Engineering teams to embed AI copilots and autonomous agents into core procurement workflows.
• Contribute to CI/CD, MLOps, and cloud-native deployment strategies for AI services.
• Mentor junior engineers and drive best practices in AI architecture, governance, and responsible AI development.

• 7–10 years of professional software development experience, with at least 3+ years focused on AI/ML or Generative AI systems.
• Strong hands-on experience building production-grade solutions using LLMs (OpenAI, Gemini/Vertex AI, Anthropic, etc.).
• Deep expertise in Agentic AI architectures, including planning, tool-calling, memory management, reasoning loops, and multi-agent coordination.
• Proven experience designing and implementing RAG pipelines, embeddings workflows, and vector search systems (e.g., Pinecone, Weaviate, Chroma, Vertex AI Vector Search).
• Hands-on experience with LangChain, LangGraph, or similar orchestration frameworks.
• Experience building and managing MCP (Model Context Protocol) servers to expose tools, data sources, and contextual memory securely to AI agents.
• Strong proficiency in Python and building scalable APIs using FastAPI/Flask or similar frameworks.
• Experience integrating AI agents with enterprise systems via APIs, event-driven architectures, and microservices.
• Practical knowledge of prompt engineering, structured outputs, tool schemas, function calling, and evaluation methodologies.
• Experience with Google Cloud (Vertex AI preferred) or AWS/Azure for deploying AI solutions in production.
• Familiarity with AI-native development tools such as Cursor, Windsurf, Copilot, or similar AI-assisted engineering platforms.
• Strong understanding of containerization (Docker), orchestration (Kubernetes), and CI/CD pipelines.
• Knowledge of AI observability, safety, governance, and responsible AI practices.
• Strong problem-solving abilities with experience working in complex enterprise SaaS environments.
• Excellent communication skills and ability to collaborate across cross-functional teams.
  
  #LI-AR1