Conversational AI Designer
Location
United States
Posted
1 day ago
Salary
Not specified
Seniority
Mid Level
Job Description
About Us
Full Potential Solutions (FPS) is a performance-based, analytically driven omnichannel solutions organization with operations in Waltham, MA, Chennai, India, Bogota, Colombia, and Manila, Philippines that puts culture and employees first. We are a rapidly growing global company, employing the best people, processes, and proprietary technology to deliver groundbreaking solutions for our clients and fulfilling careers for our employees.
We invest in our people and put culture first because we believe that happy, fulfilled teams deliver breakthrough results. FPS offers a competitive suite of benefits for our employees, including a lucrative compensation program, medical, dental, and vision benefits, and the opportunity for high-potential career growth with a fast-growing company.
Our Core Values:
Integrity - Do what’s right for everyone: clients, shareholders, partners & colleagues, TEAM is more important than self, and create an atmosphere of mutual respect
Excellence - Deliver exceptional client results, Reward and recognize performance, and Relentless pursuit of improvement
Accountability - Act like an owner, take pride in our work, Measure results (your own and our clients), Be passionate
Grace - Respect and appreciate differences, Care for one another, Humility, Make work personal
Our Mission: To create conditions within which people can thrive!
Roles and Responsibilities:
Delivery & execution
Design natural, user-friendly dialogue flows for chatbots, voice assistants, and AI-powered interfaces, balancing clarity, brevity, and tone.
Work directly with clients & product owners to translate goals and customer intents into implementation-ready conversation architectures (intents, entities/slots, prompts, confirmations, fallbacks); incorporate feedback while protecting usability, safety, and scope.
Create and maintain conversation design artifacts (conversation maps, flow diagrams, turn-by-turn scripts, prompt/reprompt libraries, escalation patterns).
Define testing coverage for designs (happy paths, edge cases, ambiguous/adversarial inputs) and support QA with structured test scenarios.
Use analytics and qualitative feedback (transcripts, drop-offs, containment, CSAT, recontact) to iterate and improve flows and prompts.
Align conversation behaviors with client brand voice and customer experience standards across channels (voice/chat).
Conversational AI platform leadership
Define voice-optimized behaviors (barge-in, disambiguation, speech-friendly phrasing,low-confidence handling)
Define chat-optimized behaviors (quick replies, progressive disclosure, rich UI patterns where applicable).
Develop and enforce conversation style guidelines (tone, reading level, inclusive language, empathy, compliance phrasing, “what not to say” constraints).
Support implementation in platforms such as Cognigy (preferred), Amazon Lex + Amazon Q ,Kore.ai, Yellow.ai, etc. Partnering with engineers & architects to optimize reusability and maintainability.
Operational excellence & Cross-functional collaboration
Define and enforce standards for reliability, observability, on-call readiness, and continuous improvement (SOPs, logging, dashboards, alerts, templates).
Participate in incident response and root-cause reviews; ensure learnings translate into durable engineering changes.
Work with security/compliance stakeholders for data handling, retention, and access control when integrating customer data sources.
Exhibit our core values: integrity, excellence, accountability and grace.
Qualifications
Work authorization/location: Must have work authorization within the United States or a U.S. citizen working abroad.
3+ years designing and delivering conversational experiences in a commercial Conversational AIplatform (not just writing scripts), such as Cognigy, Amazon Lex, Kore.ai, Yellow.ai, Dialogflow, Rasa, or equivalent.
Proven experience shipping multiple production deployments (e.g., 3+ launched assistants) with ongoing iteration based on real user data.
Multi-channel design experience: Demonstrated ability to design for both voice and chat (or deep expertise in one plus working knowledge of the other), including modality-specific best practices (e.g., barge-in/reprompts for voice; UI affordances for chat).
Conversation architecture mastery: Strong command of intent/slot (entity) modeling, dialog state management, confirmation strategies, disambiguation, and robust error handling/fallback design.
LLM + knowledge grounding competence: Experience designing LLM-assisted or knowledge-backed conversational flows (e.g., retrieval/grounding patterns, prompt + response constraints, “I don’t know” behaviors, escalation).
Practical understanding of APIs (REST), webhooks, authentication concepts, and how bots integrate with backend systems/CRMs.
Design tooling & documentation: Strong proficiency producing clear design artifacts using tools such as Miro, Voiceflow, or equivalent tools and content/version management practices for prompts/flows.
Delivery process: Experience working in Agile teams (sprint planning, grooming, story writing/acceptance criteria, iteration with QA and engineering).
Analytics & optimization: Ability to use conversation analytics to drive improvements (containment, drop-off, turn count, misunderstanding rate, deflection, CSAT), and to propose experiments and measurable success criteria.
Contact center / CX domain: Experience designing for customer service use cases (handoff to agents, intent triage, authentication, policy/compliance language, sensitive topics).
UX/UI collaboration: Strong fundamentals in UX writing and collaboration with UX/UI teams; familiarity with chat UI patterns, accessibility considerations, and multi-lingual/localization workflows.
Related Guides
Related Job Pages
More AI Engineer Jobs
Automotive Engineer with Python - Freelance AI Trainer
MindriftApply → Pass qualification(s) → Join a project → Complete tasks → Get paid. Project time expectations: Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements; This is an estimate, not a guaranteed workload, and applies only while the project is active. Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.
Please submit your CV in English and indicate your level of English proficiency. Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is pr...
Automotive Engineer with Python - Freelance AI Trainer
MindriftApply → Pass qualification(s) → Join a project → Complete tasks → Get paid. Project time expectations: Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements; This is an estimate, not a guaranteed workload, and applies only while the project is active. Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.
Please submit your CV in English and indicate your level of English proficiency. Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is pr...
Automotive Engineer with Python - Freelance AI Trainer
MindriftApply → Pass qualification(s) → Join a project → Complete tasks → Get paid. Project time expectations: Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements; This is an estimate, not a guaranteed workload, and applies only while the project is active. Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.
Please submit your CV in English and indicate your level of English proficiency. Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is pr...
Automotive Engineer with Python - Freelance AI Trainer
MindriftApply → Pass qualification(s) → Join a project → Complete tasks → Get paid. Project time expectations: Tasks are estimated to require around 10–20 hours per week during active phases, based on project requirements; This is an estimate, not a guaranteed workload, and applies only while the project is active. Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project.
Please submit your CV in English and indicate your level of English proficiency. Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is pr...
