AI Engineer — Speech & Voice Intelligence

AI Engineer — Speech & Voice IntelligenceCompany: CNTXT Type: Full-time Location: Remote-friendly / HybridAbout CNTXTCNTXT is building voice AI infrastructure for the Arabic-speaking world. We work on the hard problems — natural speech synthesis, real-time transcription, and conversational voice systems — with a focus on Arabic language quality that actually serves the region's speakers.The RoleWe're looking for an AI engineer or researcher who is passionate about voice and speech technology. You'll work directly on the models and systems that power our speech products — evaluating architectures, running fine-tuning experiments, and shipping improvements to production. This is a hands-on role that sits at the intersection of research and engineering.What Our Team Works OnSpeech Synthesis (TTS) We build and fine-tune Arabic TTS systems based on state-of-the-art generative architectures — both autoregressive models that generate speech token by token and non-autoregressive models that produce full utterances in parallel. This includes working with neural vocoders (HiFi-GAN, MelGAN, WaveGlow), audio codecs and tokenizers (EnCodec, DAC, RVQ-based systems), acoustic encoders (HuBERT, wav2vec), and diffusion-based audio decoders. A significant focus is voice cloning and zero-shot speaker adaptation for Arabic voices.Speech Recognition (ASR) We work with encoder-decoder and CTC-based ASR models (Whisper, Conformer, wav2vec 2.0) to build accurate, low-latency Arabic transcription. This includes streaming inference, domain adaptation, and language model integration for Arabic dialect robustness.Speech-to-Speech We are building end-to-end voice interaction pipelines that chain ASR, language understanding, and TTS — with hard constraints on latency. This involves voice activity detection (VAD), speaker diarization, speech enhancement, and optimizing the full stack for real-time performance.Arabic Language Challenges Arabic presents unique challenges across the whole stack: diacritization (tashkil) is critical for TTS pronunciation accuracy, dialect variation (MSA, Gulf, Levantine, Egyptian, Maghrebi) affects both synthesis and recognition quality, and training data for many dialects remains scarce. A big part of our work is closing these gaps.What You'll Work OnBenchmark and evaluate TTS and ASR models on Arabic test sets — measuring WER, speaker similarity (SIM), naturalness, and dialect coverage across MSA and regional varietiesFine-tune pretrained TTS models on curated Arabic data — including ablations on diacritized vs. undiacritized input, dialect-specific training splits, and voice prompt conditioningExperiment with audio tokenizer and codec configurations — comparing discrete RVQ representations against continuous latent approaches and their effect on Arabic phoneme accuracyBuild and maintain Arabic speech data pipelines — audio sourcing, normalization, diacritization, quality filtering, and manifest generation for model trainingOptimize models for production serving — streaming chunk generation, KV cache tuning, quantization, and batched inference for low-latency Arabic TTS and ASREvaluate and adapt speech-to-speech pipelines — integrating ASR, LLM, and TTS components with attention to end-to-end latency and Arabic conversational qualityWhat We're Looking ForStrong foundations in machine learning and deep learningHands-on experience training or fine-tuning neural models — domain matters less than depthComfortable with Python, PyTorch, and the HuggingFace ecosystemAble to read research papers and translate ideas into experiments independentlyClear communicator who can work across research and engineeringNice to HaveNative or fluent Arabic speaker — a real advantage when evaluating synthesis naturalness and dialect qualityPrior work with speech or audio models (ASR, TTS, speaker verification, codec, VAD, enhancement, or similar)Familiarity with Arabic linguistic structure, diacritization tools, and NLP preprocessing for ArabicExperience with inference optimization — quantization, speculative decoding, CUDA kernels, or serving frameworks (vLLM, TensorRT)Publications or open-source contributions in speech or audioWhat We OfferWork at the frontier of Arabic voice AI — a genuinely underserved, high-impact areaDirect influence on product and research directionSmall, focused team — your work ships and mattersCompetitive compensation and remote flexibility