DontApply.Club
Login Register

Senior Voice AI Engineer

Pentasia — Malta · Posted ~1 week ago

Senior Hybrid

Skills

Voice AI Speech-to-Text Text-to-Speech Large language models Real-time systems Low-latency streaming Voice Activity Detection Conversational AI Prompt engineering System optimization LiveKit STT LLMs TTS VAD

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

A technology organization is seeking a senior voice AI engineer to design and build production-grade real-time conversational systems. You will combine speech recognition, large language models, speech synthesis, streaming, voice activity detection, turn-taking, and advanced prompting to create responsive and natural voice interactions.

Highlights

Cutting-edge senior engineering role focused on real-time conversational voice AI. The position offers the opportunity to build low-latency production systems combining speech recognition, LLM reasoning, and speech synthesis while solving challenging performance and reliability problems.

Description

Senior AI Voice Engineer. Location: Malta. Work model: Hybrid. We are looking for a Senior Voice AI Engineer to design and build real-time conversational voice systems that integrate seamlessly into our engagement workflows. This role focuses on low-latency, production-grade voice pipelines, combining Speech-to-Text (STT), LLM reasoning, and Text-to-Speech (TTS) into cohesive, high-quality experiences. You’ll be working on systems that need to feel natural, responsive, and human-like, operating under strict performance and reliability constraints. Key Responsibilities: Design and build real-time voice AI pipelinesDevelop and optimize low-latency streaming systems using tools like LiveKitImplement and fine-tune Voice Activity Detection (VAD) and turn-taking logicEngineer robust prompting strategies for conversational AI (multi-turn, context-aware flows)Integrate LLMs with voice interfaces for agent-assist and autonomous interactionsOptimize for latency, interruption handling, and conversational naturalnessEvaluate and improve speech recognition accuracy and voice synthesis qualityWork closely with product and operations to embed voice AI into player engagement workflowsEnsure scalability, observability, and fault tolerance of real-time systems Required Skills / Experience: 5+ years of experience in software engineering, with strong exposure to real-time or AI systemsHands-on experience with voice AI components including STT, TTS & VADExperience with LiveKit or similar real-time communication frameworks (WebRTC, media pipelines)Strong experience with LLMs and prompt engineering for conversational systemsProficiency in PythonUnderstanding of latency optimization and streaming architecturesExperience building and deploying production-grade systems