Foundever logo
Foundever

Foundever® is the next-generation service leader reinventing #CustomerExperience (#CX).

Conversational AI Engineer

Location

Spain

Posted

5 days ago

Salary

0

Seniority

Mid Level

No structured requirement data.

Job Description

Conversational AI Engineer

Foundever

Role Description The Conversational AI Engineer is responsible for developing and deploying Conversational AI solutions (chatbots and voicebots), using LLMs, Agentic AI, NLU, and RAG technologies. This role executes technical implementations and integrations across environments while translating business and conversational requirements into scalable, secure, and maintainable technical solutions. It is responsible for defining the technical architecture, integration strategy, APIs, authentication, data flows, AI orchestration, and deployment approach, ensuring compliance with enterprise standards and best practices. The role leads technical discovery and feasibility assessments, implementing and integrating Conversational AI platforms with enterprise systems, CRMs, knowledge bases, telephony, backend services, and third-party applications. It combines expertise in solution architecture, prompt engineering, knowledge base structuring, AI orchestration, and system integration to enable end-to-end automation and continuous improvement. The Conversational AI Engineer also ensures safe and reliable AI model behavior through guardrails, testing, proactive monitoring, troubleshooting, fine-tuning and optimization of prompts, retrieval strategies, and AI model configurations. Additionally, the role oversees STT/TTS configuration and maintenance, voice infrastructure, telephony integration, observability, and performance optimization to guarantee high-quality voice experiences and seamless system integration. Qualifications - Knowledge of Conversational AI, including RAG, LLMs and NLU - Degree or background in engineering or development - Experience working with Conversational AI platforms and deploying AI bots - Experience with speech technologies, including STT (speech-to-text) and TTS (text-to-speech) - Experience in deployment and integration, including APIs and system integrations - Experience with prompt engineering - Ability to clearly document architectures, configurations, and deployment procedures - Fluent in written and spoken English Requirements - Implement, deploy, and maintain Voicebot and Chatbot solutions across development, technical testing/UAT, and production environments - Perform technical discovery and feasibility assessments by evaluating integrations, APIs, data sources, platform capabilities, architecture constraints, technical dependencies, and implementation requirements - Define and maintain the technical solution architecture, including integration architecture, APIs, authentication, data flows, AI orchestration, and deployment approaches, ensuring scalability, security, maintainability, and alignment with enterprise standards - Implement and manage system integrations to enable seamless automation across enterprise platforms, applications, and backend systems - Ensure safe and reliable AI model by implementing safeguards and governance measures - Engineer and refine prompts to guide LLM behavior and ensure precise, context-aware, and business-aligned responses - Structure and optimize knowledge bases to ensure accurate and context-aware responses - Select, configure, integrate, and optimize the most suitable STT and TTS technologies for each use case and language, considering accuracy, latency, voice quality, cost, and platform compatibility to ensure reliable voice performance - Implement and support telephony integrations for voicebot solutions - Apply technical best practices and recommendations for LLMs, Agentic AI, and hybrid AI solutions (NLU + LLM) - Implement new integrations and backend components required to support Conversational AI solutions - Document solution architectures, technical specifications, configurations, integrations, and deployment processes to ensure maintainability and knowledge sharing; Detect and mitigate technical risks and issues - Identify and mitigate technical risks, issues, and dependencies throughout the project lifecycle - Define technical standards, implementation guidelines, and reusable architecture patterns to ensure consistency, scalability, and maintainability across Conversational AI solutions - Collaborate with Conversational Designers, Delivery Managers, Data Analysts, business stakeholders, and cross-functional teams to deliver scalable and business-aligned Conversational AI solutions Benefits - Remote work flexibility - Opportunity to work with leading brands in the CX industry - Access to cutting-edge technology and innovative solutions

Related Job Pages

More LLM Engineer Jobs

EWOR logo

AI Infrastructure Co-Founder / Head of Sales

EWOR

For those who think in decades and build in days.

LLM Engineer7 days ago
Full TimeRemoteTeam 201-500Since 2020H1B No Sponsor

• You will own, build, and run your startup in fields such as AI Infrastructure • You will embark on an extensive personal development journey crafted by unicorn founders and follow a fully customised programme enhancing your goal, time, and energy management • You will receive support in hiring through our network to over 50,000 professionals and advice as well as best practices from serial entrepreneurs • You will receive intensive coaching to make your startup ready to raise millions in funding • You will iterate your product with us until having reached product-market-fit and receive support in building up a sales force or creating a marketing engine respectively

United Kingdom

Role Description - 6+ years hands-on SEO experience - Currently employed at one of the following (this is the filter that matters): - A reputable Indian B2B SaaS company with a real organic growth function (e.g. Zoho, Freshworks, Postman, Chargebee, Razorpay, BrowserStack, Whatfix, Hasura, Zluri, and peers of that caliber) - A B2B-focused SEO/content agency serving Western clients (e.g. Animalz, Siege Media, Omniscient Digital, Foundation, Grow & Convert, Growfusely, or comparable boutiques) - An in-house growth/SEO role at a Western SaaS company, working remotely from India - SaaS or B2B background — not e-commerce, not affiliate, not local SEO - Demonstrable experience with US/Canada search markets Requirements - Must be strong in: - Technical SEO (Core Web Vitals, schema, crawl/index, site architecture, log analysis) - Content & search intent strategy - AI search optimization, Generative Engine Optimization (GEO), LLM SEO - Ethical authority building (no PBNs, no link schemes) - SEO analytics (GA4, GSC, Ahrefs/SEMrush, Screaming Frog) - Linking SEO work to business outcomes — pipeline, MQLs, revenue, not just traffic - Written and spoken English at a level comfortable for North American stakeholder communication

India
Armada logo

Technical Trainer – AI Infrastructure Products, Part-time

Armada

At Armada, we are committed to fostering a work environment where everyone is given equal opportunities to thrive. As an equal opportunity employer, we strictly prohibit discrimination or harassment based on race, color, gender, religion, sexual orientation, national origin, disability, genetic information, pregnancy, or any other characteristic protected by law. This policy applies to all employment decisions, including hiring, promotions, and compensation. Our hiring is guided by qualifications, merit, and the business needs at the time.

LLM Engineer9 days ago
Part TimeRemoteTeam 51-200H1B Sponsor

• We are seeking a patient, articulate, and technically fluent Part-Time Technical Trainer to join our team on an on-demand basis. • This role sits closer to technical marketing than software development — you will need to understand and confidently use our GPUaaS platform and surrounding ecosystem, but you are not expected to develop on top of it. • Your primary focus will be two-fold: (1) building customer-centric demo content that replaces engineering-centric recordings with relatable, use-case-driven flows, and (2) delivering hands-on, guided training sessions at customer sites around the world. • Work is project-based, averaging roughly one week per month, and is ideal for an experienced professional who wants to stay engaged without a full-time commitment. • This is a non-converting contract engagement. Hours and travel are not guaranteed week-to-week; when a training trip is scheduled, you go — when it is not, there is no work. • The predictable portion of the role is demo and curriculum creation; the training delivery side fluctuates.

United States
$110 - $140 / hour
Full TimeRemoteTeam 1,001-5,000Since 1994H1B No Sponsor

• Desarrollo de Personas Sintéticas de IA: Diseñar y desarrollar personas impulsadas por inteligencia artificial utilizando grafos de conocimiento, RAG, GraphRAG y datos empresariales. • Desarrollo de soluciones basadas en LLMs: Implementar funcionalidades avanzadas utilizando modelos de lenguaje para generar insights y apoyar la toma de decisiones. • Diseño de flujos de IA agéntica: Crear y optimizar agentes inteligentes capaces de automatizar tareas complejas y generar información de valor para el negocio. • Desarrollo Backend y Fullstack: Construir APIs, microservicios e integraciones escalables utilizando tecnologías modernas y buenas prácticas de ingeniería de software. • Gestión de datos e integración: Trabajar con plataformas de datos empresariales, conocimiento estructurado y no estructurado para alimentar soluciones de IA. • Optimización y evaluación de soluciones IA: Mejorar continuamente la calidad, precisión, rendimiento y escalabilidad de los componentes desarrollados. • Colaboración multidisciplinar: Trabajar estrechamente con Product Owners, arquitectos, equipos técnicos y stakeholders de negocio dentro de metodologías ágiles.

Spain