Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Oleh Siloch, a results-driven AI software engineer with 9+ years of experience designing and deploying intelligent systems that blend cutting-edge AI capabilities with robust backend engineering. I build real-time, low-latency conversational platforms, voice assistants, and retrieval-based search systems, delivering practical business outcomes through thoughtful architecture and collaboration. I specialize in FastAPI, Django, Node.js, LangChain, React, Next.js, and cloud infrastructure (AWS, GCP, Azure). I enjoy turning complex problems into scalable, maintainable solutions and continuously improving AI inference pipelines for speed and accuracy in production environments.…Hi, I’m Oleh Siloch, a results-driven AI software engineer with 9+ years of experience designing and deploying intelligent systems that blend cutting-edge AI capabilities with robust backend engineering. I build real-time, low-latency conversational platforms, voice assistants, and retrieval-based search systems, delivering practical business outcomes through thoughtful architecture and collaboration. I specialize in FastAPI, Django, Node.js, LangChain, React, Next.js, and cloud infrastructure (AWS, GCP, Azure). I enjoy turning complex problems into scalable, maintainable solutions and continuously improving AI inference pipelines for speed and accuracy in production environments.

Oleh Siloch

AI Engineer, Full Stack Developer, Back-End Developer, +2





Hi, I’m Oleh Siloch, a results-driven AI software engineer with 9+ years of experience designing and deploying intelligent systems that blend cutting-edge AI capabilities with robust backend engineering. I build real-time, low-latency conversational platforms, voice assistants, and retrieval-based search systems, delivering practical business outcomes through thoughtful architecture and collaboration. I specialize in FastAPI, Django, Node.js, LangChain, React, Next.js, and cloud infrastructure (AWS, GCP, Azure). I enjoy turning complex problems into scalable, maintainable solutions and continuously improving AI inference pipelines for speed and accuracy in production environments.…Hi, I’m Oleh Siloch, a results-driven AI software engineer with 9+ years of experience designing and deploying intelligent systems that blend cutting-edge AI capabilities with robust backend engineering. I build real-time, low-latency conversational platforms, voice assistants, and retrieval-based search systems, delivering practical business outcomes through thoughtful architecture and collaboration. I specialize in FastAPI, Django, Node.js, LangChain, React, Next.js, and cloud infrastructure (AWS, GCP, Azure). I enjoy turning complex problems into scalable, maintainable solutions and continuously improving AI inference pipelines for speed and accuracy in production environments.

Available to hire

Hi, I’m Oleh Siloch, a results-driven AI software engineer with 9+ years of experience designing and deploying intelligent systems that blend cutting-edge AI capabilities with robust backend engineering. I build real-time, low-latency conversational platforms, voice assistants, and retrieval-based search systems, delivering practical business outcomes through thoughtful architecture and collaboration.

I specialize in FastAPI, Django, Node.js, LangChain, React, Next.js, and cloud infrastructure (AWS, GCP, Azure). I enjoy turning complex problems into scalable, maintainable solutions and continuously improving AI inference pipelines for speed and accuracy in production environments.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

Ukrainian

Fluent

English

Advanced

Work Experience

Senior AI / Full-Stack Engineer at Digital A Go Go SRL

July 1, 2023 - Present

Led the end-to-end design and deployment of an AI-powered conversational platform with real-time voice assistants, chatbot workflows, and retrieval-based search. Built a real-time voice booking assistant using ElevenLabs Conversational AI, WebSocket streaming (PCM16 @ 16kHz), VAD, barge-in detection, and queued TTS across Flutter and web apps. Developed LLM-powered support tools (summarization, smart replies, semantic FAQ search) reducing human operator load by ~55%. Architected RAG pipelines with pgvector, Pinecone, and FAISS to boost FAQ relevance and task resolution speed. Optimized backend APIs and microservices (FastAPI, Django, Node.js) with caching, async queues, and high-traffic query optimization. Implemented privacy-first data ingestion with RBAC, encryption, and tokenized storage for HIPAA/PCI-DSS compliance. Owned CI/CD and infrastructure automation on AWS/GCP, with observability stacks (Prometheus, Grafana, Sentry). Built live dashboards (Next.js/React) for transcription p

AI & Backend Engineer at Synthesia

March 1, 2023 - October 15, 2025

Architected multimodal AI backends for a personalized video generation platform, reducing rendering latency by 45% through GPU inference optimization, model parallelism, and asynchronous orchestration. Built and deployed LLM-driven parsing engines to extract tone, pacing, and narrative structure from scripts, enabling dynamic storyboarding. Developed scene-aware segmentation and voice intent recognition combining Whisper, LLaMA 2, Stable Diffusion, and TTS. Engineered end-to-end pipelines integrating Whisper ASR, custom TTS, diffusion models, and LangChain orchestration for automated content generation at scale. Designed a FAISS-based semantic asset retrieval engine, improving search relevance and content recommendation speed. Built a real-time collaborative backend using Django Channels, Redis Streams, and WebRTC with <200ms latency, enabling synchronous media editing with a React/Next.js frontend. Implemented prompt-chaining and retrieval workflows for dynamic scene generation and in

Junior AI Engineer at Institute of Molecular Biology and Genetics, NAS of Ukraine

April 1, 2021 - October 15, 2025

Applied machine learning and statistical modeling to biomedical datasets for early-stage cancer detection from gene expression profiles. Designed data preprocessing and feature engineering pipelines for large genomic datasets. Contributed to pose estimation models for medical imaging using OpenPose and TensorFlow, achieving reduced computation through model optimization. Collaborated with biomedical researchers to validate ML models on clinical datasets and integrate them into research workflows. Built data visualization dashboards and analytics pipelines to support clinical decision-making and research analysis.

Senior AI / Full-Stack Engineer at Digital A Go Go SRL

July 1, 2023 - Present

Led end-to-end design and deployment of an AI-powered conversational platform integrating real-time voice assistants, chatbot workflows, and retrieval-based search. Built a real-time voice booking assistant with ElevenLabs Conversational AI, WebSocket streaming, VAD, barge-in detection, and queued TTS across Flutter and web apps. Developed LLM-powered tools (summarization, smart replies, semantic FAQ search) reducing human operator load by ~55%. Architected RAG pipelines with pgvector, Pinecone, and FAISS to boost retrieval accuracy and speed. Optimized backend APIs with advanced caching, async task queues, and high-traffic performance. Implemented privacy-first data ingestion with RBAC and encryption; managed CI/CD, containerized services on AWS/GCP; built live dashboards and observability interfaces.

AI & Backend Engineer at Synthesia

March 1, 2023 - October 15, 2025

Architected multimodal AI backends for personalized video generation; reduced rendering latency by 45% via GPU inference optimization and model parallelism. Built LLM-driven parsing engines for tone, pacing, and narrative structure; developed scene-aware segmentation and voice intent recognition (Whisper, LLaMA 2, Stable Diffusion, TTS). Created end-to-end multimodal pipelines integrating Whisper ASR, TTS, diffusion models, and LangChain orchestration. Implemented a FAISS-based semantic asset retrieval engine and a real-time collaborative backend using Django Channels, Redis Streams, and WebRTC with sub-200ms latency. Established observability and deployed GPU inference clusters with Docker/Kubernetes.

Junior AI Engineer at Institute of Molecular Biology and Genetics, NAS of Ukraine

April 1, 2021 - October 15, 2025

Applied ML to biomedical datasets for early-stage cancer detection from gene expression profiles; built data preprocessing and feature engineering pipelines; contributed to pose estimation models for medical imaging (OpenPose/TensorFlow) and integrated ML workflows into clinical research. Built data visualization dashboards and analytics pipelines to support decision making and research.

Senior AI | Full-Stack Engineer at Digital A Go Go SRL

July 1, 2023 - Present

Led end-to-end design and deployment of an AI-powered conversational platform with real-time voice assistants, chatbot workflows, and retrieval-based search. Built a real-time voice booking assistant using ElevenLabs Conversational AI, WebSocket streaming, VAD, barge-in detection, and queued TTS across Flutter and web apps. Developed LLM-powered tools (summarization, smart replies, semantic FAQ search) with LangChain, OpenAI API, and Hugging Face models, reducing operator load by ~55%. Architected RAG pipelines with pgvector, Pinecone, and FAISS to improve FAQ accuracy and task resolution. Optimized backend APIs/microservices (FastAPI, Django, Node.js), caching (Redis), and async queues (Celery) for high-traffic environments. Implemented privacy-first ingestion with RBAC, encryption, and tokenized storage for HIPAA/PCI DSS compliance. Owned CI/CD and infra automation: Dockerized services, deployments on AWS/GCP, and observability with Prometheus, Grafana, and Sentry. Built real-time da

AI & Backend Engineer at Synthesia

March 1, 2023 - October 15, 2025

Architected multimodal backends for an AI-powered personalized video generation platform, reducing rendering latency by 45% via GPU inference optimization, model parallelism, and asynchronous orchestration. Built LLM-driven parsing engines to extract tone, pacing, narrative structure, and character intent from scripts for dynamic storyboarding. Developed scene-aware segmentation and voice intent recognition (Whisper, LLaMA 2, Stable Diffusion, TTS) to enhance content transformation workflows. Engineered end-to-end multimodal pipelines (Whisper ASR, custom TTS, diffusion models, LangChain) for scalable content generation. Implemented FAISS-based semantic asset retrieval to improve search relevance. Built a real-time collaborative backend (Django Channels, Redis Streams, WebRTC) with sub-200ms latency, supporting synchronous media editing and live previews. Implemented prompt-chaining and retrieval workflows for dynamic scene generation. Integrated observability to monitor latency and mo

Junior AI Engineer at Institute of Molecular Biology and Genetics, NAS of Ukraine

April 1, 2021 - October 15, 2025

Applied ML to biomedical datasets for early cancer detection from gene expression profiles; designed data preprocessing and feature engineering pipelines; contributed to pose estimation models for medical imaging (OpenPose, TensorFlow) with model compression to reduce computation. Collaborated with biomedical researchers to validate ML models on clinical data and integrate them into research workflows. Built data visualization dashboards and analytics pipelines to support clinical decision-making and research.