Lead AI Architect Opportunity at Kandou
Kandou is seeking a Lead AI Architect to design, build, evaluate, and deploy advanced AI agent systems targeted at real-world applications. This role goes beyond conversational assistants, focusing on the creation of complex analytical workflows, knowledge-based reasoning systems, controlled inference pipelines, tool-using agents, and transparent decision-support architectures.
Key Responsibilities
- Design and implement real-world agentic AI systems using modern agent frameworks and orchestration tools.
- Develop agentic workflows that include complex analytical pipelines, multi-step research workflows, tool-using agents, knowledge-grounded agents, and structured decision-support systems.
- Work with knowledge-based AI architectures, such as retrieval-augmented generation, knowledge graphs, symbolic rules, structured domain models, ontologies, and hybrid reasoning systems.
- Develop and apply mechanisms for controlling inference, including planning constraints, reasoning policies, guardrails, validation layers, tool-use control, and human-in-the-loop checkpoints.
- Explore and implement neuro-symbolic approaches for agentic reasoning.
- Build transparent AI methods that ensure agent behaviour is traceable, explainable, testable, and auditable.
- Create evaluation and testing frameworks for agentic systems, which include benchmark tasks, regression tests, failure-mode analysis, and performance measurement.
- Develop full-stack prototypes and production applications, integrating backend services, APIs, databases, frontend interfaces, model providers, and orchestration layers.
- Collaborate with researchers, engineers, product teams, and domain experts to create reliable agentic workflows from real-world problems.
- Stay current with developments in agentic AI, reasoning systems, LLM orchestration, AI evaluation, and applied neuro-symbolic methods.
Required Experience
- Proven experience in developing real-world AI agents or agentic workflows.
- Focus on agentic reasoning, including tasks such as planning, tool use, and autonomous task completion.
- Experience in industrial AI development, academic research, or ideally both.
- Hands-on experience with knowledge-based agentic systems.
- Experience implementing methods for controlling reasoning or inference.
- Familiarity with neuro-symbolic AI concepts or hybrid reasoning architectures.
- Experience designing transparent, inspectable, or explainable AI methods.
- Practical experience in evaluating and testing agentic reasoning.
- Full-stack web development experience, including backend APIs and frontend applications.
Technical Skills
- Strong Python engineering skills.
- Experience with modern LLM and agentic AI frameworks, including LangChain and OpenAI SDK.
- Backend development experience, proficient with APIs and databases.
- Familiarity with frontend technologies such as React or Next.js.
- Understanding of vector and graph databases, semantic search, and knowledge graph tooling.
- Experience in reasoning system architectures and the representation of knowledge.
Qualifications and Portfolio
- Open-source contributions and/or portfolio projects related to agentic AI.
- Experience in domains such as scientific analysis, enterprise knowledge management, or legal/financial analysis.
- Familiarity with AI system design for production, focusing on observability and reliability.
- Experience integrating LLMs with external tools or systems.
- Desirable: publications in prominent NLP/ML/AI conferences.
Apply online using the form below. Please note that only applications matching the job profile will be considered.