Description

You will own and deliver critical components of the AI agent assist stack, including STT, summarization, and scalable data pipelines.

This role is on-site.

Responsibilities

• Lead implementation of LLM-based features including summarization, sentiment detection, and auto-disposition.
• Fine-tune and evaluate models (Whisper, GPT, HuggingFace) for vernacular language support.
• Build and deploy LangChain pipelines for prompt engineering, QA tagging, and agent assist.
• Architect scalable data pipelines using PostgreSQL, Redis, and Kafka with secure access controls.
• Guide junior ML engineers and define coding and data standards.

Required Skills

• 5+ years total experience, with 2-5 years in ML/AI/Data Engineering.
• Hands-on experience with Whisper, LangChain, HuggingFace, or similar frameworks.
• Solid Python skills with FastAPI preferred for building RESTful APIs.
• Proficiency in SQL and PostgreSQL.
• Experience with CI/CD, Docker, Kubernetes (K3s/K8s), Redis, and Kafka/RabbitMQ.
• Strong understanding of NLP, STT, summarization, and emotion tagging.

Preferred Skills

• Experience with multilingual models (Hindi, Tamil, Bengali) or Rasa/Coqui TTS.
• Background in SaaS, Contact Center, or CRM ecosystems.

Key Skills

Education

Any Graduate