Artificial Intelligence Engineer-Agentic & Voice Intelligence

Job Title: AI Engineer Agentic & Voice Intelligence

Location: Bengaluru (Work from Office)

Experience: 3+ Years

About the Role

We are looking for a highly skilled AI Engineer with expertise in Agentic AI systems, Voice

Intelligence, and Audio Analytics. The ideal candidate will design and develop intelligent

calling agents, speech-to-text models, and advanced audio analysis solutions that enhance

humanmachine communication and real-time interaction capabilities.

Key Responsibilities

• Design, develop, and deploy AI Agents capable of automating conversations,

handling calls, and responding intelligently using LLMs and agentic AI frameworks.

• Implement and optimize transcription models (ASR/STT) for high-accuracy real-time

voice-to-text conversion.

• Build audio analytics pipelines for tone, emotion, and speaker analysis.
• Research, fine-tune, and integrate voice analysis models (speaker identification,

sentiment, and emotion detection).

• Collaborate with backend and ML teams to integrate AI features into production

applications.

• Work with large speech datasets for model training, evaluation, and improvement.
• Optimize model performance for latency, accuracy, and scalability.
• Stay updated with the latest advancements in Agentic AI, speech processing, and

voice analytics technologies.

Must-Have Skills

• Strong hands-on experience with AI Agent frameworks (LangChain, AutoGen,

CrewAI, or similar).

• Proven experience building or integrating calling AI systems (voice bots, telephony

AI, real-time audio response).

• Deep understanding of speech recognition / transcription models (Whisper,

Deepgram, AssemblyAI, or custom ASR).

• Expertise in audio analytics and voice signal processing speech segmentation,

tone & emotion detection, feature extraction (MFCCs, spectrograms, etc.).

• Proficiency in Python, and libraries such as PyTorch, TensorFlow, SpeechBrain,

librosa, torchaudio.

• Experience with LLM integration (OpenAI, Anthropic, Gemini, etc.) for intelligent

responses.

• Understanding of SCORM, APIs, and cloud deployment (AWS/GCP/Azure).

Good-to-Have Skills

• Knowledge of TTS (Text-to-Speech) and Voice Cloning models.
• Familiarity with real-time communication tools (WebRTC, SIP, Twilio).
• Experience building RAG pipelines and multimodal AI systems.
• Exposure to vector databases (Pinecone, Chroma, Weaviate).
• Strong analytical and problem-solving skills.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data

Science, or related field.

• 3+ years of experience in AI, NLP, or Voice AI development.
• Demonstrated experience in deploying AI/ML models in production environments.

Desired Candidate Profile:

• Experience with AI agent tools like LangChain, AutoGen, or CrewAI.
  
• Hands-on experience building or integrating voice bots or calling AI systems.
  
• Strong knowledge of speech recognition tools like Whisper, Deepgram, or AssemblyAI.
  
• Solid understanding of audio analysis — tone, emotion, segmentation, and speech features like MFCCs.
  
• Good Python skills and experience with libraries like PyTorch, TensorFlow, SpeechBrain, librosa, torchaudio.
  
• Ability to integrate LLMs (OpenAI, Anthropic, Gemini) into applications.
  
• Knowledge of APIs, SCORM, and deploying projects on AWS/GCP/Azure.