Lead AI Architect

ph3Lead AI Architect /h3 pKandou is looking for a Lead AI Architect to help design, build, evaluate, and deploy advanced AI agent systems for real-world use cases. This role focuses on agentic systems that go beyond conversational assistants: complex analytical workflows, knowledge‑based reasoning systems, controlled inference pipelines, tool‑using agents, and transparent decision‑support architectures. /p pPostulation uniquement en ligne – merci de mentionner sous source (ORP). /p pLocation: 1025 St‑Sulpice VD (VD). Full‑time, immediately, permanent. /p h3Key Responsibilities /h3 ul liDesign and implement real‑world agentic AI systems using modern agent frameworks and orchestration tools. /li liDevelop agentic workflows that go beyond chat, including complex analytical pipelines, multi‑step research workflows, tool‑using agents, knowledge‑grounded agents, and structured decision‑support systems. /li liWork with knowledge‑based AI architectures such as retrieval‑augmented generation, knowledge graphs, symbolic rules, structured domain models, ontologies, and hybrid reasoning systems. /li liDevelop and apply mechanisms for controlling inference, including planning constraints, reasoning policies, guardrails, validation layers, tool‑use control, and human‑in‑the‑loop checkpoints. /li liExplore and implement neuro‑symbolic approaches for agentic reasoning, combining LLM‑based reasoning with symbolic, rule‑based, graph‑based, or formally structured methods. /li liBuild transparent AI methods that make agent behaviour traceable, explainable, testable, and auditable. /li liCreate evaluation and testing frameworks for agentic systems, including benchmark tasks, regression tests, failure‑mode analysis, trace inspection, robustness testing, and task‑level performance measurement. /li liDevelop full‑stack prototypes and production applications, integrating backend services, APIs, databases, frontend interfaces, model providers, and orchestration layers. /li liCollaborate with researchers, engineers, product teams, and domain experts to translate ambiguous real‑world problems into reliable agentic workflows. /li liStay current with developments in agentic AI, reasoning systems, LLM orchestration, AI evaluation, and applied neuro‑symbolic methods. /li /ul h3Required Experience /h3 ul liStrong multi‑project experience developing real‑world AI agents or agentic workflows. /li liDemonstrated focus on agentic reasoning, including planning, decomposition, tool use, multi‑step inference, workflow execution, or autonomous task completion. /li liExperience in industrial AI development, academic research, or ideally both. /li liHands‑on exposure to knowledge‑based agentic systems such as agents grounded in knowledge graphs, structured documents, domain rules, ontologies, databases, or retrieval systems. /li liExperience with methods for controlling reasoning or inference, such as guardrails, constrained planning, validation layers, policy‑based tool use, symbolic checks, or deterministic workflow components. /li liFamiliarity with neuro‑symbolic AI concepts or hybrid reasoning architectures. /li liExperience designing transparent, inspectable, or explainable AI methods. /li liPractical experience with agentic reasoning evaluation, testing, benchmarking, observability, or failure analysis. /li liFull‑stack web development experience, including backend APIs and frontend application development. /li /ul h3Technical Skills /h3 ul liStrong Python engineering skills. /li liExperience with modern LLM and agentic AI frameworks, especially LangChain, LangGraph, OpenAI SDK / OpenAI Agents SDK, retrieval‑augmented generation systems, tool/function calling, multi‑agent or multi‑step workflow orchestration, agent evaluation and tracing tools. /li liExperience with backend development, APIs, databases, and cloud or deployment environments. /li liExperience with frontend technologies such as React, Next.js, TypeScript, or similar frameworks. /li liFamiliarity with vector databases, graph databases, semantic search, structured data pipelines, or knowledge graph tooling. /li liSomeone who thinks beyond prompt engineering and is experienced in the architecture of reasoning systems: how agents decide what to do, how inference is constrained, how knowledge is represented, how workflows are verified, and how complex AI systems can be made reliable for real‑world use. /li /ul h3Qualifications and Portfolio /h3 ul liMature open‑source contributions and/or portfolio projects related to agentic AI, LLM systems, knowledge‑based AI, or neuro‑symbolic reasoning. /li liExperience building AI systems in domains such as scientific analysis, enterprise knowledge management, decision support, research automation, legal/financial/technical analysis, or complex operational workflows. /li liExperience with production‑grade AI system design, including observability, monitoring, testing, security, latency, cost control, and reliability. /li liFamiliarity with human‑in‑the‑loop systems, provenance tracking, workflow auditability, or regulated environments. /li liExperience integrating LLMs with external tools, APIs, databases, code execution environments, or analytical engines. /li liDesirable: publications at main NLP/ML/AI conferences. /li /ul pFor more information, visit /p /p #J-18808-Ljbffr