Senior ASR Engineer – Enterprise IVR & Production ML

Omilia; España; Hybrid; PHP 5,639,000 - 9,398,000; Full time

Benefits offered by this job

Apple gear

Vacation days

Professional development

Job summary

Omilia is seeking an ASR Engineer to own end-to-end tuning, deployment, and live performance of our ASR technology for enterprise IVR and voice-channel deployments. You will lead ASR solutions from requirements through go-live and ongoing optimization, coordinating with multiple teams to meet tight deadlines.

You will drive WER/SER improvements with acoustic and language model design, contribute to automation, and ensure reliability across global regions.

Qualifications

• 5+ years hands-on ASR/speech engineering in live IVR deployments
• Experience supporting customers, ideally in regulated industries
• Proficient with Kaldi or equivalent; LM/DM design and decoder tuning required
• Strong programming in Python; Linux environment comfortable (Bash/Java/C++ acceptable)
• English fluency and strong stakeholder communication
• Ability to own ambiguous, production-critical problems independently

Responsibilities

• Tune ASR grammars, acoustic models, and language models for new locales, domains, and customer vocabularies
• Design, train, and fine-tune acoustic and language models with measurable WER/SER improvement
• Investigate and resolve production ASR issues and engage with stakeholders
• Run customer working sessions and translate technical tradeoffs for non-technical audiences
• Represent ASR delivery in cross-functional forums with Product, Support, and PM
• Build and maintain grammar-generation and automation pipelines to speed up releases

Skills

English communication

Client engagement

Education

Bachelor's degree in CS or equivalent

Tools

Kaldi

Python

Bash

Java

C++

Job description

Omilia is seeking an ASR Engineer to own end-to-end tuning, deployment, and live performance of our ASR technology for enterprise IVR and voice-channel deployments. You will lead ASR solutions from requirements through go-live and ongoing optimization, coordinating with multiple teams to meet tight deadlines.

You will drive WER/SER improvements with acoustic and language model design, contribute to automation, and ensure reliability across global regions.