First seen by Alion on Nov 17, 2026.
We are looking for a hands-on Senior ML & ASR Engineer with strong experience in production-grade Machine Learning, Automatic Speech Recognition (ASR), multilingual speech processing and Medical NLP.
The role involves building and maintaining end-to-end speech AI pipelines for real-world clinical environments, including noisy hospital OPDs, low-bandwidth networks and multilingual, code-mixed conversations across Indian languages.
The ideal candidate should have experience deploying and optimising speech recognition models, machine translation systems and GPU-based inference pipelines. Exposure to healthcare, healthtech or health insurance is essential.
Key Responsibilities:
- Multilingual ASR & Speech Recognition: Design, build and maintain low-latency streaming ASR systems for multiple Indian languages. Fine-tune and evaluate speech recognition models for clinical use cases involving medical vocabulary, code-mixed speech and diverse accents. Implement Voice Activity Detection (VAD), background noise suppression and audio signal processing techniques. Optimise models for real-time inference through quantisation, streaming decoding, batching and GPU memory management. Develop offline and edge-deployable ASR pipelines for devices operating in low-connectivity environments. Build evaluation pipelines and clinical audio datasets to monitor accuracy, latency and model performance.
- Machine Translation: Develop and maintain translation systems that convert regional-language transcripts into Hindi or English. Fine-tune translation models using clinical text, medical terminology, symptom descriptions, dosage instructions and doctor notes. Identify and resolve inference bottlenecks to maintain production latency SLAs.
- Medical NLP & Clinical Intelligence: Collaborate with clinical teams on symptom extraction, specialist routing and clinical summarisation models. Improve clinical NLP accuracy through entity recognition, medical coding and structured extraction from unstructured speech. Work on integrating speech outputs with clinical NLP pipelines. Ensure outputs align with HL7, FHIR and ABDM requirements and remain auditable for regulatory and insurance purposes.
- Model Serving & GPU Infrastructure: Manage model-serving pipelines on GPU infrastructure, including process management, worker configuration, startup and logging. Maintain reproducible GPU environments, including framework versions, CUDA compatibility and package dependencies. Monitor inference latency, GPU utilisation, error rates and uptime. Evaluate on-premise versus cloud GPU infrastructure and contribute to cost optimisation.
Skills
ASR, Automatic Speech Recognition, ML, Machine Learning, NLP, Natural Language Processing, Speech

