The problemOff-the-shelf speech models are trained for clean English. Our users speak dozens of African and Middle Eastern dialects, over noisy lines, code-switching mid-sentence. The gap between a model that works in the demo and one that works for them is the whole job. You'll own the fine-tuning that closes it: taking base speech and language models and making them actually understand, and sound natural to, the people we serve.The problemOff-the-shelf speech models are trained for clean English. Our users speak dozens of African and Middle Eastern dialects, over noisy lines, code-switching mid-sentence. The gap between a model that works in the demo and one that works for them is the whole job. You'll own the fine-tuning that closes it: taking base speech and language models and making them actually understand, and sound natural to, the people we serve.Why it's hard hereThis is low-resource, messy-data territory. For a lot of the dialects we care about, the clean training corpus you'd want doesn't exist, so you'll be building it: sourcing, cleaning, labeling, and augmenting audio, then running the fine-tunes and proving they moved the numbers that matter. Word error rate on a real accent, not a benchmark. Naturalness a native speaker would actually sign off on. You'll live in the loop between data, training runs,



and evaluation.What You'll OwnTraining/ fine-tuning STT and TTS (and where relevant, the language layer) for our target dialects and acoustic conditionsThe training data pipeline: sourcing, cleaning, labeling, and augmentation for low-resource languagesEvaluation you can trust: WER on real-world audio, naturalness, robustness to noise and code-switchingFeeding real production performance back into the next round of trainingWhat We're Looking ForStrong applied ML experience, with models you've fine-tuned and shipped to productionHands-on with speech: ASR/STT and/or TTS, and the training stack around them (PyTorch, etc.)Real experience with the unglamorous parts: data collection, cleaning, and labeling for messy audioRigor around evaluation, especially where standard benchmarks don't reflect your usersComfort owning a model end to end and shipping fast with imperfect dataNice to haveLow-resource, multilingual, or multi-dialect speech workExperience with modern speech architectures (Whisper-family, speech-to-speech, neural TTS)A feel for the latency and size constraints of serving these models in real timeGenuine interest in emerging markets or speech techThe setupYou’ll work directly with our CTO on a team of ~10 that ships constantly. High ownership, short path to decisions, real users the day you ship. London-based, in-office.#J-18808-Ljbffr

📌 Voice Ai Engineer (Real de Gandía)
🏢 AethexAI
📍 Real de Gandía