About the Role :

We are looking for a Principal AI Engineer to build AI-native products at the intersection of Generative AI, Agentic AI, Voice AI, and real-time data engineering.

This is a hands-on engineering role focused on building production-grade AI systems for voice automation, intelligent agent assistance, real-time decisioning, and multilingual conversational experiences.

Key Responsibilities :

- Design, develop, and deploy production-grade AI/ML and Generative AI solutions.

- Lead implementation of LLM-powered features including summarization, sentiment detection, auto-disposition, escalation tagging, and agent assistance.

- Build and deploy LangChain/LangGraph-based pipelines for prompt engineering, QA tagging, agent assist, and intelligent workflows.

- Develop Voice AI and Conversational AI solutions including voice bots, AI voice agents, and real-time voice assistance.

- Fine-tune and evaluate models such as Whisper, GPT, Hugging Face, and Rasa for multilingual and Indian vernacular language support.

- Prototype and productionize emotion recognition, contextual agent responses, and real-time AI assistance.

- Build scalable inference services using FastAPI, Docker, and Kubernetes.

- Integrate AI capabilities into core product systems including Dialer, CRM, IVR, and communication platforms.

- Optimize model serving, latency, concurrency, and deployment strategies for production workloads.

- Architect scalable data pipelines using PostgreSQL, Redis, Kafka, and ETL/ELT workflows.

- Build real-time analytics and feedback loops to continuously improve AI models and product performance.

- Ensure secure and compliant data storage, retrieval, and access controls aligned with DPDP/GDPR requirements.

- Work closely with Product, Engineering, and UX teams to convert business problems into scalable AI solutions.

- Guide junior ML and data engineers while establishing strong engineering, coding, and data standards.

- Contribute to AI strategy, model governance, and data infrastructure roadmap.

Mandatory Requirements :

- 6+ years of overall software engineering experience, including 3+ years of hands-on AI/ML, Generative AI, Applied AI, or Machine Learning engineering experience.

- Strong hands-on experience building and deploying LLM, RAG, Agentic AI, and Generative AI applications.

- 1+ year of recent hands-on experience in Voice AI / Voice Bots / Conversational AI / AI Voice Agents / Speech AI / Contact Center Automation.

- Strong Python expertise with experience building scalable AI/ML applications, APIs, microservices, or backend systems.

- Hands-on experience with LangChain, LangGraph, Hugging Face, LlamaIndex, CrewAI, AutoGen, Whisper, OpenAI SDKs, or equivalent AI/GenAI frameworks.

- Experience designing production-grade AI architectures with focus on scalability, latency, reliability, and high concurrency.

- Strong understanding of LLM integration, prompt engineering, RAG, model evaluation, inference, and AI application development.

- Experience working with real-time data and event-driven architectures is highly relevant for the role.

- Strong communication, technical leadership, and problem-solving skills.

Preferred :

- Experience with AWS, Azure, or GCP.

- Hands-on MLOps, model serving, AI deployment platforms, and cloud-native architectures.

- Experience with multilingual/vernacular AI, especially Indian languages.

- Exposure to WebRTC, real-time communications, Dialers, IVR, CRM integrations, or Contact Center platforms.