Data Scientist — Call Analytics

About the role

We are looking for a Data Scientist specialized in call analytics to own the quality of speech‑to‑text (STT) and text‑to‑speech (TTS) systems for Indian languages. You will work on latency, code‑switching and telephony‑grade audio pipelines that power our voice platform.

Key responsibilities

• Fine‑tune and evaluate ASR and TTS models for Hindi, Telugu, Tamil and English code‑mixed speech.
• Build offline evaluation datasets and regression test suites for each model release.
• Collaborate with backend engineers to enable streaming inference at 8–16 kHz.
• Document model cards, failure modes and language‑specific tuning guidelines.
• Ship models from research to production, ensuring robustness and low latency.

Required profile

• B.E./B.Tech or M.Tech in Computer Science, Electrical Engineering or a related field.
• At least 2 years of hands‑on experience in speech processing or natural language processing.
• Proven ability to take research prototypes to production environments.

Required skills

• Python programming.
• Deep‑learning frameworks such as PyTorch (or equivalent).
• Experience with ASR and TTS model development.
• Knowledge of speech/NLP evaluation metrics and regression testing.
• Familiarity with streaming inference pipelines.