> Markdown version of [/jobs/ext/2808225-conversational-ai-architect-nice-cognigy](https://www.wearedevelopers.com/jobs/ext/2808225-conversational-ai-architect-nice-cognigy). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Conversational AI Architect (NiCE Cognigy) - **Company:** Natilik - **Location:** Greater London, UK (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** JavaScript (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Software Debugging, Software Design Patterns, Node.Js, Performance Tuning, Systems Integration, Twilio, WebRTC, Core Voice Platform, Data Logging, Chatbots, Large Language Models, IT Architecture, Facebook Flow, Low Latency, Virtual Agents, Profanity (Software), Restful APIs, Natural Language Understanding, Api Management, Cisco - **Published:** September 9, 2026 - **Apply:** https://www.collegerecruiter.com/job/2858098832-conversational-ai-architect-nice-cognigy ## About the Role * At least 2-3 years' experience designing and delivering conversational AI, voice AI, or agentic AI solutions. * Strong hands-on Cognigy AI architecture and delivery experience, including Flows, Voice Gateway, Agentic AI tool calling, LLM Prompt nodes, Knowledge AI, xApps, Playbooks, Insights, environment management, and reusable solution patterns. * Strong practical understanding of LLM prompting, tool design, tool orchestration, structured tool results, hallucination prevention, prompt grounding, guardrails, and when to use deterministic logic or NLU alongside agentic reasoning. * Good working knowledge of conversation design principles, including intent journeys, task flows, fallback paths, repair prompts, turn-taking, escalation points, voice-friendly wording, and reducing customer friction. * Strong JavaScript understanding for reviewing Code Nodes, validation logic, payload mapping, API response handling, context manipulation, logging, and custom flow behaviour. * Experience designing secure REST API integrations, PII-safe handling, authentication patterns, error handling, observability, and production support models. * Strong voice-agent architecture experience, including STT/TTS selection, multilingual recognition, DTMF, barge-in, end pointing, transfers, hang-up logic, silence handling, latency, and speech tuning. * Ability to debug complex issues using transcripts, context, input, tool arguments, Voice Gateway logs, API responses, Insights, and Code Node logs., * Cognigy certification; advanced conversation design or voice UX experience, including persona design, tone-of-voice definition, dialogue repair strategy, multilingual copy design, IVR-to-voice-agent migration, containment optimisation, and usability testing. * Contact-centre architecture experience * Agent Copilot and Cisco Finesse integration experience * SSML and advanced TTS tuning * SIP/WebRTC, Twilio or similar voice connectivity * CRM, case-management, or CCaaS integrations * Experience defining guardrail frameworks for prompt leakage prevention, scope control, profanity filtering, hallucination prevention, and speech-safe output. ## Description Our Conversational AI Architect owns the overall solution design, architecture, design standards, integration strategy, security approach, platform patterns, technical governance, conversation design approach, and design sign-off. The AI Architect may also be required to undertake or support AI Engineer responsibilities where necessary. These include implementing the agreed design, testing and debugging, maintaining documentation, and escalating any issues where the design is unclear, presents risks, is incomplete, or is blocked., Our Conversational AI Architect ensures the solution is not just functional, but scalable, secure, maintainable, testable, and suitable for production voice and chat use cases. This role should provide the technical and conversational design clarity that allows our Cognigy AI Engineers to deliver confidently and consistently., * Own the end-to-end Cognigy solution design across the assigned use cases. * Define the architecture, design patterns, flow structure, agentic AI strategy, tool-calling approach, integration model, security controls, guardrails, multilingual approach, voice experience, xApp strategy, reporting model, and production readiness standards. * Decide when to use agentic AI, deterministic flows, NLU, Knowledge AI, xApps, or human handover. * Define reusable patterns for LLM Prompt nodes, tool schemas, Resolve Tool Actions, context management, API integrations, fallback handling, escalation, and error recovery. * Provide technical direction to Cognigy AI Engineers, review implementation quality, unblock delivery issues, validate design decisions, and own solution sign-off. * Lead stakeholder workshops, demos, design reviews, risk reviews, and technical governance. ## Related Videos - [Hello JARVIS - Building Voice Interfaces for Your LLMS](https://www.wearedevelopers.com/videos/1641-hello-jarvis-building-voice-interfaces-for-your-llms) - [How Cisco embraced a DevOps culture within its network engineering team](https://www.wearedevelopers.com/videos/99-how-cisco-embraced-a-devops-culture-within-its-network-engineering-team) - [Transforming Education: A Journey from interactive Markdown to Remote-Labs](https://www.wearedevelopers.com/videos/941-transforming-education-a-journey-from-interactive-markdown-to-remote-labs) - [20 billion requests a week: Upgrading Twilio's API gateway at scale](https://www.wearedevelopers.com/videos/100234-20-billion-requests-a-week-upgrading-twilio-s-api-gateway-at-scale) - [Raise your voice!](https://www.wearedevelopers.com/videos/10-raise-your-voice) - [Your Infrastructure Is Not a Playground: AI Agents for Infra Done Right](https://www.wearedevelopers.com/videos/2084-your-infrastructure-is-not-a-playground-ai-agents-for-infra-done-right) ## Related Articles - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [The Prompt Engineer ✍️](https://www.wearedevelopers.com/magazine/216-the-prompt-engineer) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)