Senior Conversational AI Engineer (Speech & NLU)

Capgemini is seeking a highly skilledSenior Conversational AI Engineer to design, build, and optimize next-generationspeech recognition, natural language understanding (NLU), and conversational AI systems. The role focuses on transforming traditional DTMF-based IVR systems into anintelligent, multilingual conversational platform handling over10 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) for80+ customer intents across 5 languages

• Optimize speech recognition fortelephony environments (8kHz audio, noisy conditions)
• Achieve and maintain95%+ transcription accuracy
• Handledialects, code-switching, and informal speech (e.g., Singlish, Arabic variants)
• Implementlanguage detection and intelligent routing
• DevelopDTMF fallback mechanisms for failure scenarios
• Tuneacoustic models for enhanced performance

2. Natural Language Understanding (NLU) Development

• Build and trainintent classification models (50+ intents) across multiple languages
• Developentity extraction models (accounts, amounts, dates, names, transactions)
• Optimize models forregional and dialect-specific language nuances
• Designdisambiguation logic for unclear user inputs
• Implementcontext handling for multi-turn conversations
• Achieve90%+ intent classification accuracy
• Buildcontinuous learning pipelines from production data

3. Conversational Design & Dialogue Optimization

Designnatural and intuitive conversational flows

• Collaborate with VUI designers for enhanced user experience
• Implementreal-time sentiment and urgency detection
• Enableemotion-aware adaptive responses
• Designintelligent escalation and IVR-to-agent handoff flows
• Continuously optimize journeys using analytics and feedback

4. Performance Monitoring & Analytics

• Monitorcall quality, latency, and failure scenarios
• ConductQA reviews for complex interactions
• Identify and fixmisrouting and recognition errors
• Generatetraining datasets from failed interactions
• ExecuteA/B testing for flow and model improvements
• Analyzecall data, recognition accuracy, and NLU performance metrics

5. Documentation & Collaboration

• Collaborate withAI engineers, contact center teams, backend developers, and product stakeholders
• Evaluate and recommendspeech AI platforms and tools
• Maintain comprehensivedocumentation for grammars, models, and flows

Experience

5+ years inspeech recognition, conversational AI, or NLU and Avaya

• 3+ years working withIVR / voice assistant platforms
• 2+ years experience withLLMs / Generative AI
• Exposure tocontact center platforms (Genesys, Avaya, Dialogflow)
• Domain experience infinancial services (preferred)

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.

https://www.capgemini.com/us-en/about-us/who-we-are/