LILT
AI Researcher / ML Engineer (ASR & Speech Specialist)
Washington D.C · Principal
Sponsorship not specifiedDetected 28 days ago
PythonAndroidData StructuresAlgorithmsGitgRPCWebSocketsMachine LearningDeep LearningTensorFlowPyTorchData ScienceNLPLLMsAgentic AIA/B TestingSalesforceElectrical EngineeringSignal ProcessingWebflowResearchCommunicationCollaborationProblem Solving
About the role
- ABOUT LILT AI is changing how the world communicates - and LILT is leading that transformation.
- We use cutting-edge AI, machine translation, and human-in-the-loop expertise to translate content faster, more accurately, and more cost-effectively without compromising on brand, voice, or quality.
- Our company virtues-Work together, win together; Find a way or make one; Quicker than they expect; Quality is Job 1-guide everything we do.
Responsibilities
- Customization & Domain Adaptation: Design and deploy highly scalable algorithms for dynamic vocabulary insertion, contextual biasing, and language model (LM) personalization to precisely capture customer-specific terminology, acronyms, and product names.
- Evaluation: Implement automated framework evaluations to benchmark model performance, rigorously tracking Word Error Rate (WER), Character Error Rate (CER), embedding-based metrics, latency budgets (RTF), and computing efficiency profiles under varying acoustic environments.
- Agentic Benchmarking: Develop pioneering multilingual benchmarks for end-to-end conversational AI agents, including speech-to-text and text-to-speech components, and targeting the weaknesses of state-of-the-art frontier models.
- Real-Time & Batch Speech Systems: Partner with core engineering teams to build, optimize, and maintain high-throughput pipelines optimized for both ultra-low latency real-time streaming inference and high-efficiency asynchronous (batch) multi-channel speech analysis.
- Speech Pipeline Engineering: Develop and refine standard auxiliary components of the speech processing chain, including Voice Activity Detection (VAD), speaker diarization, punctuation restoration, noise/acoustic normalization, and audio pre-processing filters.
- Speech Domain Expertise: Minimum of 3-5 years of dedicated professional experience developing ASR systems, speech-to-text translation pipelines, or advanced audio processing models.
- Multilingual Engineering: Professional exposure to building zero-shot multilingual speech systems or managing cross-lingual acoustic phonology data.
- Design and deploy highly scalable algorithms for dynamic vocabulary insertion, contextual biasing, and language model (LM) personalization to precisely capture customer-specific terminology, acronyms, and product names.
- Develop pioneering multilingual benchmarks for end-to-end conversational AI agents, including speech-to-text and text-to-speech components, and targeting the weaknesses of state-of-the-art frontier models.
- Partner with core engineering teams to build, optimize, and maintain high-throughput pipelines optimized for both ultra-low latency real-time streaming inference and high-efficiency asynchronous (batch) multi-channel speech analysis.
Requirements
- Candidates must be U.S. citizens or nationals, or otherwise eligible to obtain any required government access authorization.
- Advanced proficiency with PyTorch or equivalent frameworks, along with extensive experience utilizing dedicated speech toolkits such as Whisper, NVIDIA NeMo, Hugging Face Transformers, Kaldi, ESPnet, or SpeechBrain.
- You have personally taken a non-trivial model through conversion, including resolving unsupported operations and dynamic-shape or decoder-loop issues.
- Working knowledge of mobile NPU/DSP acceleration on the Android SoC landscape (Qualcomm QNN / Hexagon, GPU, and NNAPI delegates) and the trade-offs across Snapdragon, MediaTek, and Google Tensor.
Skills
- AI is changing how the world communicates - and LILT is leading that transformation.
Benefits
- Analytical Problem Solving: Ability to break down ambiguous business or product requirements into deterministic, actionable machine learning experimentation frameworks.
- Collaborative Communication: Strong capability to communicate intricate technical machine learning complexities to non-technical stakeholders across product, design, and executive leadership.
Company info
- Our founders, Spence and John met at Google working on Google Translate.
- As researchers at Stanford and Berkeley, they both worked on language technology to make information accessible to everyone.
- While together at Google, they were amazed to learn that Google Translate wasn't used for enterprise products and services inside the company.The quality just wasn't there.
- So they set out to build something better.
- LILT was born.
- LILT has been a machine learning company since its founding in 2015.
- At the time, machine translation didn't meet the quality standard for enterprise translations, so LILT assembled a cutting-edge research team tasked with closing that gap.
- While meeting customer demand for translation services, LILT has prioritized investments in Large Language Models, human-in-the-loop systems, and now agentic AI.
- With AI innovation accelerating and enterprise demand growing, the next phase of LILT's journey is just beginning.
- What sets our platform apart:
- Brand-aware AI that learns your voice, tone, and terminology to ensure every translation is accurate and consistent
- Agentic AI workflows that automate the entire translation process from content ingestion to quality review to publishing
- 100+ native integrations with systems like Adobe Experience Manager, Webflow, Salesforce, GitHub, and Google Drive to simplify content translation
- Human-in-the-loop reviews via our global network of professional linguists, for high-impact content that requires expert review
Visa & Work Authorization
- If you have any concerns, require accommodations, or would like to opt-out of the use of AI in our hiring process, please let us know at recruiting@lilt.com.
This listing is sourced directly from LILT's careers page and normalized into a canonical job model.