s
suscrabmychinal

Hamid Ali Khan

@suscrabmychinal
Pakistan
Inglese, Urdu
Alcune informazioni sono riportate in lingua inglese.
Chi sono
Software engineer building graphics-heavy simulation software and production AI systems. I develop simulation applications in C++ with Qt and OpenGL, focusing on performance. Alongside this, I build and deploy Python-based voice agents that help patients book clinic appointments. These combine LangChain-driven conversation workflows, FastAPI backends, and speech-to-text/text-to-speech pipelines, running on servers I manage myself. I enjoy building scalable, well-optimized software, whether that means squeezing frames out of a renderer or cutting latency in a live voice conversation.... Continua a leggere

Competenze

s
suscrabmychinal
Hamid Ali Khan
offline • 
Tempo di risposta medio: 1 ora

Consulta i miei servizi

App desktop
I will build your web or desktop app with cpp python and ai

Esperienza lavorativa

Software Engineer

NASTP • Full time

Apr 2025 - Present • 1 yr 7 mos

Software engineer building graphics-heavy simulation software and production AI systems. At NASTP, I develop simulation applications in C++ with Qt and OpenGL/GLSL, focusing on performance and responsive real-time rendering under heavy workloads. Alongside this, I build and deploy Python-based voice agents that help patients book clinic appointments. These combine LangChain-driven conversation workflows, FastAPI backends, and speech-to-text/text-to-speech pipelines, running on servers I manage myself. I enjoy building scalable, well-optimized software, whether that means squeezing frames out of a renderer or cutting latency in a live voice conversation. Open to software engineering roles in C++/graphics, simulation, or AI/voice systems, and to collaborations in these areas.

AI Engineer

Wosler Corp • Full time

Aug 2024 - Sep 2026 • 2 yrs 1 mo

Working on a voice-to-voice AI agent for customer conversations: Designed and built a microservices architecture to handle different components of the conversation flow Integrated Google Speech-to-Text and ElevenLabs TTS for voice processing Implemented LangGraph to manage conversation states and context Created a FastAPI backend to handle real-time communication Collaborated with the team to improve voice recognition accuracy and response times