Mert Akgun
Lead Software Engineer at Vyvo
Istanbul, Türkiye Turkey
Summary
🤩
Rockstar🎓
Top SchoolMert Akgun is a Lead Software Engineer based in Istanbul with six years of experience building low-latency, production-grade systems and AI-driven agents. He designs and deploys real-time, resource-efficient pipelines for multimodal Retrieval-Augmented Generation and GPU-accelerated workloads, and has hands-on experience with H100/A100 infrastructures, SurrealDB/Qdrant, and containerized auto-scaling. His background spans embedded real-time networking (TSN, eBPF/XDP) and system administration at scale, giving him deep expertise in both kernel-level optimizations and cloud-native deployment patterns. As an open-source backend contributor to pipecat-ai, he enhanced multimodal LLM services with robust text/audio handling and WebSocket improvements—showing a focus on practical, production-ready integrations. Colleagues rely on him to bridge low-level performance engineering with modern AI stack requirements, and he often surfaces non-obvious optimizations from his embedded and ops-driven experience.
6 years of coding experience
9 years of employment as a software developer
Bachelor of Engineering - BE Computer Engineering, Bachelor of Engineering - BE Computer Engineering at Sivas Cumhuriyet Üniversitesi
English, Turkish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
websocket10
websockets-client10
api10
websocket-client10
python10
back-end-development10
ai10
client-websocket10
apidoc9
Programming languages (10)
Github contributions (5)
pipecat-ai/pipecat
Oct 2024 - Jan 2025
Open Source framework for voice and multimodal conversational AI
Role in this project:
Back-end Developer
Back-end DeveloperContributions:3 reviews, 4 PRs, 8 comments in 3 months
Contributions summary:Mert primarily contributed to the `GeminiMultimodalLiveLLMService`, enhancing its functionality by adding text handling, response modality configuration, and full text response management. These changes included implementing methods to control audio and text output, adding text buffers for complete responses, and improving the WebSocket connection setup. Additionally, the user added example code to demonstrate the usage of the Gemini service with text-only responses and made several improvements to the example file.
aichatbot-frameworkchatbotsreal-timevoice
imsakg/sarucaController
Aug 2021 - Dec 2021
Contributions:40 commits in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.