Jobs via Dice
Job Description
Our client is a leading provider of advanced analytics solutions for the public safety sector. They process and analyze large volumes of recorded audio data to support investigations and improve operational efficiency. This role focuses on enhancing audio quality and enabling voice biometrics at scale.
Responsibilities
Design and build solutions to improve audio quality of call recordings to enable accurate voice biometrics, at scale.
Apply DSP techniques for noise reduction, voice activity detection, and channel separation.
Develop and integrate audio processing scripts into scalable data pipelines.
Collaborate with ML team to optimize audio for embedding generation.
Technical Environment Tools: AWS, ffmpeg for audio processing, Amazon Transcribe. Audio formats: MP3, FLAC; stereo and mono recordings. Data pipelines are integrated with AWS services for transcription and analytics.
Qualifications
Deep understanding of audio codecs, compression artifacts, bitrates, and sampling theory.
Ability to apply noise reduction, voice activity detection (VAD), preamble trimming, and channel separation at scale.
Experience with speaker diarization & voice printing, clustering, similarity measures, and handling overlapping speech.
Command‑line audio processing and shell scripting skills (ffmpeg, sox, aubio). Familiarity with integrating scripts into data pipelines.
Design and deployment of scalable, high‑volume audio processing solutions.
Skills
Digital Signal Processing, Applied Acoustics, voice transcription, codec, sampling theory, noise reduction, voice activity detection, VAD, DSP, voice printing, speaker diarization, speaker diarisation, command‑line scripting, shell, ffmpeg, data pipelines, MP3, FLAC, overlapping speech, voice data, audio recording, embeddings, Python, Machine learning, Artificial intelligence, librosa, pyannote, torchaudio, AWS Transcribe, AWS, cloud audio processing, devops, cloud integration, bash scripting.
Experience Level Entry Level
Job Type & Location Contract position based out of Austin, TX.
Pay & Benefits
Salary: $50.00 – $65.00 per hour.
Benefits (subject to eligibility and length of employment): medical, dental & vision; critical illness, accident and hospital coverage; 401(k) retirement plan; life insurance; short‑ and long‑term disability; health spending account; transportation benefits; employee assistance program; time off / leave (PTO, vacation, sick leave). Benefits are subject to change.
Workplace Type This is a fully remote position.
Application Deadline Position is anticipated to close on Dec 3, 2025.
Equal Opportunity Employer Statement The company is an equal opportunity employer and will consider all applications without regard to race, sex, age, color, religion, national origin, veteran status, disability, sexual orientation, gender identity, genetic information, or any characteristic protected by law.
#J-18808-Ljbffr
Responsibilities
Design and build solutions to improve audio quality of call recordings to enable accurate voice biometrics, at scale.
Apply DSP techniques for noise reduction, voice activity detection, and channel separation.
Develop and integrate audio processing scripts into scalable data pipelines.
Collaborate with ML team to optimize audio for embedding generation.
Technical Environment Tools: AWS, ffmpeg for audio processing, Amazon Transcribe. Audio formats: MP3, FLAC; stereo and mono recordings. Data pipelines are integrated with AWS services for transcription and analytics.
Qualifications
Deep understanding of audio codecs, compression artifacts, bitrates, and sampling theory.
Ability to apply noise reduction, voice activity detection (VAD), preamble trimming, and channel separation at scale.
Experience with speaker diarization & voice printing, clustering, similarity measures, and handling overlapping speech.
Command‑line audio processing and shell scripting skills (ffmpeg, sox, aubio). Familiarity with integrating scripts into data pipelines.
Design and deployment of scalable, high‑volume audio processing solutions.
Skills
Digital Signal Processing, Applied Acoustics, voice transcription, codec, sampling theory, noise reduction, voice activity detection, VAD, DSP, voice printing, speaker diarization, speaker diarisation, command‑line scripting, shell, ffmpeg, data pipelines, MP3, FLAC, overlapping speech, voice data, audio recording, embeddings, Python, Machine learning, Artificial intelligence, librosa, pyannote, torchaudio, AWS Transcribe, AWS, cloud audio processing, devops, cloud integration, bash scripting.
Experience Level Entry Level
Job Type & Location Contract position based out of Austin, TX.
Pay & Benefits
Salary: $50.00 – $65.00 per hour.
Benefits (subject to eligibility and length of employment): medical, dental & vision; critical illness, accident and hospital coverage; 401(k) retirement plan; life insurance; short‑ and long‑term disability; health spending account; transportation benefits; employee assistance program; time off / leave (PTO, vacation, sick leave). Benefits are subject to change.
Workplace Type This is a fully remote position.
Application Deadline Position is anticipated to close on Dec 3, 2025.
Equal Opportunity Employer Statement The company is an equal opportunity employer and will consider all applications without regard to race, sex, age, color, religion, national origin, veteran status, disability, sexual orientation, gender identity, genetic information, or any characteristic protected by law.
#J-18808-Ljbffr