Senior AI Engineer – Agentic Systems
Summary
Senior AI Engineer at Xurpas who designs, builds, and deploys production-grade autonomous AI agents and multi-agent systems using LLMs (LangChain, CrewAI, AutoGen, LangGraph), Python, RAG, and vector databases, integrating with enterprise APIs and cloud platforms while applying Responsible AI and LLMOps practices.
About the role
We are seeking a highly skilled Senior AI Engineer with 5 to 7 years of professional experience to design, develop, and deploy autonomous AI agents and multi-agent systems. In this role, you will build intelligent workflows that reason, plan, execute complex tasks, and seamlessly interact with enterprise applications. You will leverage Large Language Models (LLMs), cutting-edge agent orchestration frameworks, and cloud AI platforms to automate business processes and drive operational efficiency.
Key responsibilities
Design and develop production-grade Agentic AI solutions utilizing advanced LLMs and agent frameworks
Build autonomous agents capable of reasoning, planning, tool execution, and multi-step workflows, as well as complex multi-agent orchestrated systems
Integrate AI agents with enterprise systems, APIs, internal databases, and modern cloud services to power business automation
Implement robust memory systems, dynamic context management, RAG (Retrieval-Augmented Generation), and knowledge-grounding capabilities
Apply Responsible AI principles, rigorous governance, data security, and compliance controls throughout the entire solution lifecycle
Conduct ongoing testing, evaluation, monitoring, and performance optimization of AI agents in live production environments
Partner directly with business stakeholders to identify high-impact Agentic AI use cases and translate them into functional requirements
Author detailed technical documentation, build reusable frameworks, and establish engineering best practices for the AI development team
About you
5 to 7 years of professional experience
Strong technical expertise in Agentic AI frameworks (e.g., LangChain, CrewAI, AutoGen, or LangGraph) paired with advanced Python development skills
Exceptional verbal and written communication skills to articulate complex AI concepts to both technical teammates and business stakeholders
Proven experience working with foundational models (OpenAI, Anthropic, open-source models) for reasoning, function calling, and tool usage
Solid foundation in backend engineering, API integration, and handling structured/unstructured data
Experience with vector databases (e.g., Pinecone, Chroma, Milvus) and optimization of RAG pipelines
Familiarity with enterprise cloud platforms (AWS, Azure, or GCP) and AI orchestration deployment
Knowledge of MLOps / LLMOps practices for monitoring drift, latency, and costs of agentic workflows