Senior Conversational AI Engineer (Speech & NLU)

Capgemini is seeking a highly skilled Senior Conversational AI Engineer to design, build, and optimize next-generation speech recognition, natural language understanding (NLU), and conversational AI systems . The role focuses on transforming traditional DTMF-based IVR systems into an intelligent, multilingual conversational platform handling over 10 million annual interactions across multiple languages with high accuracy and natural user experience.

Key Responsibilities

1. Speech Recognition & Grammar Engineering

Design and develop speech grammars (GRXML, ABNF) for 80+ customer intents across 5 languages

• Optimize speech recognition for telephony environments (8kHz audio, noisy conditions)
• Achieve and maintain 95%+ transcription accuracy
• Handle dialects, code-switching, and informal speech (e.g., Singlish, Arabic variants)
• Implement language detection and intelligent routing
• Develop DTMF fallback mechanisms for failure scenarios
• Tune acoustic models for enhanced performance

2. Natural Language Understanding (NLU) Development

• Build and train intent classification models (50+ intents) across multiple languages
• Develop entity extraction models (accounts, amounts, dates, names, transactions)
• Optimize models for regional and dialect-specific language nuances
• Design disambiguation logic for unclear user inputs
• Implement context handling for multi-turn conversations
• Achieve 90%+ intent classification accuracy
• Build continuous learning pipelines from production data

3. Conversational Design & Dialogue Optimization

Design natural and intuitive conversational flows

• Collaborate with VUI designers for enhanced user experience
• Implement real-time sentiment and urgency detection
• Enable emotion-aware adaptive responses
• Design intelligent escalation and IVR-to-agent handoff flows
• Continuously optimize journeys using analytics and feedback

4. Performance Monitoring & Analytics

• Monitor call quality, latency, and failure scenarios
• Conduct QA reviews for complex interactions
• Identify and fix misrouting and recognition errors
• Generate training datasets from failed interactions
• Execute A/B testing for flow and model improvements
• Analyze call data, recognition accuracy, and NLU performance metrics

5. Documentation & Collaboration

• Collaborate with AI engineers, contact center teams, backend developers, and product stakeholders
• Evaluate and recommend speech AI platforms and tools
• Maintain comprehensive documentation for grammars, models, and flows

Requirements

Experience

5+ years in speech recognition, conversational AI, or NLU and Avaya

• 3+ years working with IVR / voice assistant platforms
• 2+ years experience with LLMs / Generative AI
• Exposure to contact center platforms (Genesys, Avaya, Dialogflow)
• Domain experience in financial services (preferred)

Benefits

Competitive compensation and benefits package:

1. Competitive salary and performance-based bonuses
2. Comprehensive benefits package
3. Career development and training opportunities
4. Flexible work arrangements (remote and/or office-based)
5. Dynamic and inclusive work culture within a globally renowned group
6. Private Health Insurance
7. Pension Plan
8. Paid Time Off
9. Training & Development

Note: Benefits differ based on employee level.

About Capgemini

Capgemini is a global leader in partnering with companies to transform and manage their business by harnessing the power of technology. The Group is guided everyday by its purpose of unleashing human energy through technology for an inclusive and sustainable future. It is a responsible and diverse organization of over 340,000 team members in more than 50 countries. With its strong 55-year heritage and deep industry expertise, Capgemini is trusted by its clients to address the entire breadth of their business needs, from strategy and design to operations, fueled by the fast evolving and innovative world of cloud, data, AI, connectivity, software, digital engineering and platforms. The Group €22.5 billion in revenues in 2023.