Responsibilities AI/ML + LLM/NLPLead implementation of LLM-based features: summarization, sentiment detection, auto-disposition, escalation taggingFine-tune and evaluate models (Whisper, GPT, HuggingFace, Rasa) for vernacular (Indian) language supportBuild and deploy LangChain pipelines for prompt engineering, QA tagging, and agent assistPrototype emotion recognition, contextual agent replies, and real-time assist layerBuild and maintain inference pipelines using FastAPI, Docker, KubernetesIntegrate AI modules into core product features (Dialer, CRM sync, IVR)Optimize model latency and deployment strategy for high concurrency environmentsArchitect scalable data pipelines using PostgreSQL, Redis, and KafkaBuild ETL/ELT workflows to support real-time analytics, dashboards, and feedback loopsMaintain secure, compliant data storage, retrieval, and access control pipelines (DPDP, GDPR-ready) Collaboration & LeadershipWork closely with Product, Engineering, and UX to deliver features that directly impact agent productivityGuide junior ML and data engineers; define and enforce coding/data standardsContribute to AI strategy, model governance, and data infrastructure roadmapRequired Skills & QualificationsTotal experience of 10-12 years5 years of experience in ML/AI/Data Engineering with exposure to LLMs and production-grade pipelinesHands-on with Whisper, LangChain, HuggingFace, or similar frameworksSolid Python (FastAPI preferred), SQL/PostgreSQL, and experience with RESTful APIsProven experience with CI/CD, Docker, K3s/Kubernetes, Redis, Kafka/RabbitMQStrong understanding of NLP/STT/TTS, summarization, and emotion taggingAbility to work in startup-paced environments with ownership mindsetBonus SkillsExperience with multilingual models (Hindi, Tamil, Bengali)Exposure to Rasa, Coqui TTS, or OpenWA integrationsPrior work in SaaS/Contact Center/Dialer/CRM ecosystemsFamiliarity with speech emotion recognition or agent.