AI/ML Engineer
Gurugram • Full-time
We are building the next-generation AI-native, multilingual, omnichannel communication platform for emerging markets. We are looking for a hands-on AI/ML Engineer with strong Python, NLP/LLM, speech AI, and data engineering skills to contribute to our agent assist stack, including Whisper/STT, LangChain-based summarization, emotion tagging, GPT/LLM integration, and scalable data pipelines. This role is ideal for someone who has worked on production-grade AI/ML systems and wants to build real-time AI features for contact centers, dialers, CRM platforms, and customer engagement systems.
Responsibilities:
- Implement LLM-based features including call summarization, sentiment detection, auto-disposition, escalation tagging, QA tagging, and agent assist prompts
- Work with Whisper and other Speech-to-Text (STT) models for multilingual transcription
- Support model evaluation and fine-tuning for Indian languages such as Hindi, Tamil, Bengali, Marathi, and other regional languages
- Build and maintain LangChain-based pipelines for prompt engineering, summarization, QA, and agent assist use cases
- Prototype emotion recognition, contextual agent reply suggestions, real-time agent assist, and call quality analysis
- Build and deploy inference APIs using Python, FastAPI, Docker, and Kubernetes/K3s
- Integrate AI modules with Dialer, CRM Sync, IVR, Ticketing workflows, and Agent Dashboards
- Optimize AI workflows for latency, scalability, and cost efficiency
- Build scalable data pipelines using PostgreSQL, Redis, Kafka, and RabbitMQ
- Develop ETL/ELT workflows for real-time analytics, dashboards, and AI feedback loops
- Work with structured and unstructured data including call transcripts, audio metadata, customer conversations, agent actions, and CRM records
- Support secure data storage, access control, and compliance-ready pipelines
- Collaborate with backend teams to integrate AI APIs into production services
- Work closely with Product, Engineering, and UX teams to deliver AI-powered features
- Participate in architecture discussions, technical design, and implementation planning
- Follow coding standards, documentation practices, and deployment workflows
- Support testing, debugging, and production monitoring of AI services
Requirements:
- 3+ years of experience in AI/ML, NLP, Data Engineering, or Backend Engineering with AI exposure
- Hands-on experience with Whisper or other STT models
- Experience with LangChain
- Experience with HuggingFace Transformers
- Experience with OpenAI/GPT APIs or chatbot frameworks
- Strong Python programming skills
- Experience with FastAPI or similar API frameworks
- Good understanding of REST APIs and backend service integration
- Working knowledge of SQL and PostgreSQL
- Experience with Docker and basic CI/CD workflows
- Exposure to Redis, Kafka, RabbitMQ, or similar messaging systems
- Understanding of NLP concepts including summarization, sentiment analysis, intent detection, emotion tagging, and text classification
- Ability to debug model outputs, prompts, API latency, and production issues
- Comfortable working in a fast-paced startup environment
Bonus Skills:
- Experience with multilingual AI models for Indian languages
- Exposure to speech emotion recognition
- Experience with Coqui TTS, OpenWA, or voice/chat automation tools
- Prior experience in SaaS, Contact Center, Dialer, CRM, or Customer Support platforms
- Basic understanding of Kubernetes/K3s
- Experience with vector databases, embeddings, or RAG pipelines
- Familiarity with data privacy and compliance concepts such as DPDP or GDPR
Benefits:
- Build AI-native dialer and agent assist experiences for India and emerging markets
- Work on real-world multilingual AI problems involving speech, text, emotion, and automation
- Work with modern technologies including GPT, Whisper, LangChain, WebRTC, React, FastAPI, Docker, and Kubernetes
- Fast-moving startup environment with ownership and learning opportunities
- Flexible remote working
- Growth-oriented culture