Senior Data Scientist - ASR

Eka.Care; Bengaluru; On-site; INR 1,500,000 - 2,100,000; Full time

Benefits offered by this job

Open-source publication allowed

Direct collaboration with CDSO

Opportunity to publish papers

Job summary

Eka Care is advancing open-source medical ASR with Parrotlet‑A, building to normalize and understand doctor-patient conversations in India. You will push multilingual speech models, improve drug-entity accuracy, and extend to new languages and noise scenarios, delivering production-grade ASR for clinical notes.

You will lead data pipelines, evaluation, and model cards, collaborating with senior engineers and reporting to the CDSO.

Qualifications

• 2–6 years building ASR or speech models with real users
• Deep fluency in CTC, transducers, attention encoder–decoders, SSL encoders, and speech-LLMs
• Strong PyTorch and multi‑GPU training skills
• Experience with audio fundamentals and field data challenges
• Publication or open-source contributions in speech or healthcare domains

Responsibilities

• Train Parrotlet-A end-to-end for multimodal ASR
• Improve drug-name and clinical entity transcription accuracy
• Ship models to production on GPUs with optimization and evaluation
• Own data pipelines, test sets, and evaluation framework
• Publish model cards, benchmarks, and papers under Apache 2.0
• Mentor engineers and translate research into reusable training recipes

Skills

ASR models

PyTorch

multi-GPU training

speech-LLMs

clear communication

Education

MS in CS/ML

Tools

Qwen-Audio

Whisper

TensorRT

ONNX

Triton

Job description

Eka Care is a health AI company on a mission to make world-class clinical intelligence available to every doctor, patient, and healthcare enterprise.

We build the models, data infrastructure, and clinical workflows that turn everyday care (a consultation, a prescription, a lab report) into structured, interoperable health data, so that better decisions can be made at the point of care and across the enterprise, whether that is a hospital, a diagnostic lab, or an insurer. Our products, EkaScribe, EkaDoc, EkaAgents, EkaAPIs and EkaPHR, cover the full span of clinical, patient, and enterprise use cases, and plug into national digital health infrastructure such as India’s Ayushman Bharat Digital Mission.

The Role

You will own the next generations of Parrotlet-A, Eka Care’s open-source medical ASR models, and ship them into EkaScribe, which turns doctor-patient conversations across India into structured clinical notes. Indian clinics speak Hinglish, Tanglish and a dozen other code-mixed registers over phone-grade audio, with drug names no general-purpose ASR has heard. Parrotlet-A 2 Pro already beats the best general ASR models on varied benchmarks.

Your job: widen that gap, close the remaining one on drug-entity accuracy, and lead the shift to multimodal LLM-based ASR (speech-LLMs that transcribe, normalise and understand a consultation in one pass), while extending to new languages, noise conditions and clinical settings.

What You Will Do

• Train the next Parrotlet-A models end-to-end. Multimodal LLM-based ASR is the core: audio-encoder + projector + LLM-decoder models trained through modality alignment, instruction tuning and RL post-training (GRPO, DPO) on clinical-entity rewards. Alongside, CTC / RNN-T / TDT models (Parakeet, Conformer families) for low-latency streaming, all on multi-thousand-hour medical and Indic corpora.
• Win on drug names and clinical entities. Extend the contextual-biasing stack (G2P phonetic matching, WFST biasing, shallow fusion with medical LMs) so that medicines, dosages and investigations are transcribed right the first time.
• Ship to production. Serve models on GPUs: quantisation, distillation, batching, latency/throughput tuning, and A/B evaluation inside EkaScribe.
• Own the data and eval engine. Build and maintain the data pipelines, test sets and evaluation framework that tell us whether a model is ready for doctors.
• Publish and open-source. Release model cards, benchmarks and papers under Apache 2.0.
• Raise the bar for the team. Review experiments, mentor engineers, and turn research findings into reusable training recipes.

What We Are Looking For

Must have

• 2-6 years building ASR or speech models that reached real users, with at least one model you trained from data to deployment.
• Deep, hands-on fluency in one modern speech toolkit and the architectures behind it: CTC, transducers, attention encoder-decoders, SSL encoders, and speech-LLMs. You have aligned an audio encoder to an LLM, or fine-tuned one (Qwen-Audio, Whisper-encoder + LLM, Canary, Gemma-audio style), and know where they beat and where they lose to transducers.
• Strong PyTorch and multi-GPU training skills: mixed precision, distributed data loading, checkpoint surgery, and the instinct to find why a run is slow or diverging.
• Comfort with the full evaluation story: WER/CER and why they lie, entity-level metrics, calibration, and designing test sets that predict production behaviour.
• Working knowledge of audio fundamentals (resampling, codecs, VAD, noise and reverberation) and of how speech data gets messy in the field.
• Clear written communication: you can turn an experiment into a one-page finding others can act on.
• Code-mixed or low-resource Indic language ASR, including familiarity with Devanagari / Dravidian script transliteration.
• Contextual biasing, hotword boosting or LM fusion in production.
• RL or preference-based post-training for sequence models; hallucination control and timestamping in LLM-based ASR.
• Model compression and serving: TensorRT, ONNX, CTranslate2, Triton, vLLM-style batching.
• Publications or open-source contributions in speech; prior exposure to healthcare, call-centre or legal dictation domains.

Why Eka Care

• Scale that matters. Our models already process consultations for doctors across India; a point of WER here changes what goes into a patient’s record.
• Compute and data you will not find elsewhere. Multi-thousand-hour in-house clinical speech corpora, a huge text corpus for LM fusion, and dedicated GPU capacity under the IndiaAI Mission.
• Open by default. The Parrotlet family ships under Apache 2.0 / MIT; your work carries your name, in model cards and in papers.
• A small, senior team. You sit with the people building our vision, embeddings and clinical-LLM models, reporting directly to the CDSO, with no layers between an idea and a training run.