Oleksandr S.
Voice AI Engineer
Alexander specializes in the development and deployment of high-load Artificial Intelligence systems, with a particular focus on Voice AI and MLOps infrastructure. His expertise spans the entire product lifecycle: from processing terabytes of raw data and field-calibrating sensors to deploying scalable microservices in Kubernetes. He excels at transforming complex technological challenges - whether defending against synthetic deepfakes or automating industrial agriculture - into stable, production-ready solutions. With a deep background in Voice AI, Alexander has delivered a range of mission-critical projects in Audio Intelligence and Biometrics, including real-time deepfake detection and multi-modal identity verification platforms. His skill set includes working with SOTA models for Speech-to-Text (ASR), diarization, and intelligent summarization using LLM and RAG architectures. By utilizing a stack featuring NVIDIA NeMo, Whisper, and Triton Inference Server, he builds low-latency systems capable of performing efficiently under heavy computational loads.
Key Expertise
Experience
9+ years
Timezone
CET (GMT +1)
1. Deepfake Voice Detection System
Project overview:
Telecom providers and financial institutions needed a solution to detect synthetic speech and protect against voice fraud in call centers. We built a real-time deepfake detection system for streaming audio using speaker recognition, diarization, ASR, Deep Fake detector model.
Responsibilities:
- Collected and processed terabytes of real and synthetic audio.
- Created a modular training pipeline with automated KPI evaluation and CI/CD deployment to Triton.
- Built a streaming inference module with ensemble logic and GPU optimization.
Achievements:
The system was deployed in production, integrated into call center platforms, and used to flag synthetic audio segments and alert human operators in real time.
2. AI Audio Summarization & Call Analysis
Project overview:
Call center teams and financial services wanted faster review of long customer calls for compliance and support optimization. Built an AI-powered system for speech-to-text transcription, speaker separation, and intelligent summarization of conversations.
Responsibilities:
- Ingested recorded calls, diarized speakers, and generated action-point summaries using LLMs and RAG.
- Stored embeddings in vector DB for future search and audit.
- Integrated into support ticket systems for automatic context generation.
Achievements:
Reduced review time by over 70%, improved compliance documentation, and gave managers faster insights into call quality.
Key Expertise
Experience
9+ years
Timezone
CET (GMT +1)
Ready to Work with Oleksandr S.?
Voice AI Engineer
Share your project details and our team will review the match and confirm availability.
We respond within 24 hours.