Senior Agentic Ai Engineer

We are seeking a Senior Agentic AI Engineer to design, develop, and deploy production-grade AI applications using Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), and Google Cloud Platform (GCP).The ideal candidate will have strong Python development skills, hands‑on experience building agentic AI solutions, and the ability to troubleshoot complex RAG pipelines, evaluate LLM application quality, and design scalable cloud-based architectures. This role requires solid software engineering fundamentals and the ability to take AI solutions from design and development through deployment, monitoring, and continuous improvement.Key Responsibilities:
Design, develop, and maintain agentic AI applications and LLM-powered solutions for enterprise use cases.Build and orchestrate multi‑step AI workflows using LangGraph, LangChain, or similar frameworks.Develop RAG pipelines using embeddings, vector search, and retrieval optimization techniques to deliver accurate, relevant, and grounded responses.Troubleshoot RAG performance issues across document ingestion, chunking, embeddings, retrieval, reranking, context construction, and response generation.Design and implement evaluation strategies for LLM and agentic AI applications, including retrieval quality, answer relevance, groundedness, hallucination detection, and regression testing.Implement LLM observability, tracing, monitoring, and troubleshooting using Langfuse or comparable platforms.Develop and integrate MCP‑based tools and services to connect AI agents with enterprise systems, APIs, and data sources.Build RESTful APIs and backend services using Python frameworks such as FastAPI or Flask.Leverage Google Cloud services, particularly Vertex AI and BigQuery, to build and integrate cloud‑based AI solutions.Implement prompt engineering, tool calling, structured outputs, context management, and appropriate human‑in‑the‑loop controls.Apply software engineering best practices, including automated testing, version control, CI/CD, and production deployment.Implement security, data privacy, responsible AI, and governance controls appropriate for enterprise AI applications.Collaborate with product managers, architects, data engineers, and other stakeholders in an Agile delivery environment.Troubleshoot production issues and continuously improve application reliability, performance, scalability, and response quality.Required Skills and Experience:
5+ years of professional software development experience.2+ years of hands‑on experience developing agentic AI or LLM-powered applications.Strong Python programming and software engineering fundamentals.Demonstrated experience building, deploying, and supporting LLM-powered applications.Hands‑on experience with LangGraph, LangChain, or a similar AI application framework.Experience with Langfuse or another LLM observability platform.Understanding of Model Context Protocol (MCP) and its use in connecting AI agents with tools and enterprise systems.Hands‑on experience with Google Cloud services, particularly Vertex AI and BigQuery, with the ability to explain architecture decisions and service integrations.Experience developing RAG solutions using embeddings and vector search.Strong understanding of RAG troubleshooting, retrieval optimization, and techniques for improving answer quality and grounding.Experience evaluating LLM and agentic AI applications using measurable metrics, test datasets, and regression testing.Experience developing RESTful APIs using FastAPI, Flask, or a similar framework.Understanding of prompt engineering, tool calling, structured outputs, context management, and multi‑step agent workflows.Experience with automated testing, Git, CI/CD, and production deployment practices.Understanding of data privacy, AI safety, responsible AI principles, and enterprise application security.Experience working with Agile methodologies.Excellent verbal and written communication skills, including the ability to explain technical designs, troubleshooting approaches, and engineering trade‑offs.
#J-18808-Ljbffr