Model Compression Engineer Jobs

1 job found

Today

Audio AI Engineer

Dev Technology Reston, VA

Reston, VA

Today

$80k - $160k/yr Full time Ai Engineer Artificial Intelligence Asr

Apply Now

Job Description

Dev Technology is building a multilingual audio foundation to power a mobile translation experience that runs performantly on an iPhone. In this onsite role in Reston, VA, you will develop and improve a speech-to-text core, with ownership spanning multilingual ASR data, model adaptation for constrained devices, and reproducible evaluation of real-world quality.

What you’ll do

Ingest, clean, segment, label, and version multilingual audio and transcript datasets, with specific attention to code-switching and borrowed-word behavior across the target language set.
Fine-tune and compress large ASR models to meet iPhone-class memory, latency, and battery constraints while preserving transcription quality, using approaches such as LoRA/QLoRA, quantization, distillation, or other parameter-efficient and size-reduction techniques as needed.
Create model packaging that supports selecting and downloading language-specific weights on demand based on operator context (for example, pulling only Chinese ASR weights for a Chinese-speaking interview).
Build model behavior and evaluation around when to transcribe a borrowed English term as-is versus rendering it via transliteration or a native equivalent in the source language.
Develop reproducible evaluation pipelines that measure word/character error rate, latency, and robustness to factors including accent, noise, speaking rate, and code-switching, and report results against defined success criteria per language and deployment target.
Write clear model cards, dataset documentation, and evaluation write-ups so both technical and non-technical stakeholders can understand model purpose, comparisons, and known risks and limitations.

Requirements

Bachelor’s degree in Computer Science, Data Science, Machine Learning, Computational Linguistics, or a closely related field.
Strong data-engineering experience building production pipelines for large, messy, or unstructured audio and text datasets.
Hands-on experience fine-tuning or adapting speech/audio models using parameter-efficient methods (LoRA, QLoRA, adapters) and/or compression techniques (quantization, distillation, pruning) for constrained hardware.
Practical experience developing and evaluating ASR/speech-to-text models across multiple languages, including error analysis under real-world conditions such as accents, noise, and code-switching.
Strong Python and SQL skills, with experience using tools such as PyTorch, Hugging Face Transformers/PEFT, torchaudio, and librosa.
Experience deploying and monitoring production ML systems, including secure handling of sensitive audio, transcripts, and derived data in a regulated environment.
Ability to explain model behavior, tradeoffs, and limitations to both technical and non-technical stakeholders.

Technologies

Python, SQL, PyTorch
Hugging Face Transformers, PEFT
torchaudio, librosa
LoRA, QLoRA, quantization, distillation, pruning
iPhone, iOS, Swift, AVFoundation

Role scope

This position owns the speech-to-text model: its data, training/adaptation, on-device size and latency, and transcription accuracy across languages.
It does not own iOS application development, translation (source-language-to-target-language), or the Swift/AVFoundation integration layer; those are handled by a separate mobile engineering function, with close collaboration.

Salary and location

USD 80,000 - 160,000 per yearly

Reston, VA (onsite)

Benefits

Generous and flexible time-off policy
Flexible work schedules and telework options, including remote work availability for eligible projects
Career development opportunities: mentorship program, Dev University technical and management training, hands-on learning through DevLab, tuition reimbursement, and paid training opportunities
Industry-leading benefits including a choice of two health plans with dental and vision, flexible spending account, commuter benefits, life insurance, and more
401K matching with a 5% matching contribution
Regular team and company social events including an annual party, happy hours, fitness challenges, and more
Community engagement support, including employer match for donations and time off for volunteer efforts

View full job page →

Get Model Compression Engineer Jobs alerts

New Model Compression Engineer Jobs, daily.