HiringCafe
Posted 2d ago

Senior Conversational AI Engineer (Speech & NLU)

@ Capgemini
View All Jobs
Bengaluru, Karnataka, India
HybridFull Time
Responsibilities:designing grammars, training models, monitoring performance
Requirements Summary:5+ years in speech recognition, conversational AI, or NLU; IVR/voice assistant and LLMs/Generative AI experience; exposure to Genesys, Avaya, Dialogflow; financial services domain preferred.
Technical Tools Mentioned:GRXML, ABNF, LLMs, Generative AI, Genesys, Avaya, Dialogflow
Save
Mark Applied
Hide Job
Report & Hide
Job Description

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