Khubaib A.

𝗔𝗜/𝗠𝗟 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 | 𝗦𝗶𝗴𝗻𝗮𝗹 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 | 𝗥𝗲𝗮𝗹-𝗧𝗶𝗺𝗲 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 | 𝗩𝗼𝗶𝗰𝗲 𝗔𝗜 & 𝗖𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗔𝗜 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿 (𝗦𝗧𝗧/𝗧𝗧𝗦 + 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝗮𝗴𝗲𝗻𝘁𝘀) | 𝗪𝗲𝗯𝗥𝗧𝗖/𝗟𝗶𝘃𝗲𝗞𝗶𝘁 | 𝗦𝗜𝗣/𝗩𝗼𝗜𝗣 (𝗧𝘄𝗶𝗹𝗶𝗼/𝗔𝘀𝘁𝗲𝗿𝗶𝘀𝗸) I build 𝘃𝗼𝗶𝗰𝗲 𝗮𝗴𝗲𝗻𝘁𝘀 and 𝗹𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝗮𝘂𝗱𝗶𝗼/𝘃𝗶𝗱𝗲𝗼 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 that actually hold up on real calls, in production, under load. If you're fighting latency, 𝗰𝗮𝗹𝗹 𝗱𝗿𝗼𝗽𝘀, 𝗡𝗔𝗧/𝗧𝗨𝗥𝗡 𝗶𝘀𝘀𝘂𝗲𝘀, 𝗿𝗼𝗯𝗼𝘁𝗶𝗰 𝘁𝘂𝗿𝗻-𝘁𝗮𝗸𝗶𝗻𝗴, 𝗿𝗲𝗰𝗼𝗿𝗱𝗶𝗻𝗴 𝗳𝗮𝗶𝗹𝘂𝗿𝗲𝘀 or a 𝘃𝗼𝗶𝗰𝗲 𝗮𝗴𝗲𝗻𝘁 that breaks the moment a real customer interrupts it, I can take it end-to-end and ship something stable. I focus on what client's measure, response latency, barge-in handling, RTT, jitter, packet loss, concurrency and cost per call. 𝗧𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝘀𝘁𝗿𝗲𝗻𝗴𝘁𝗵𝘀 𝗶𝗻𝗰𝗹𝘂𝗱𝗲: Python, NumPy, SciPy, Pandas, Scikit-learn ML model development + evaluation Audio/signal processing pipelines Feature engineering + algorithm optimization Distributed computing concepts Real-time data handling & automation 𝗪𝗵𝗮𝘁 𝗜 𝗯𝗿𝗶𝗻𝗴 𝘁𝗼 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝘁𝗲𝗮𝗺𝘀: Research-backed algorithm design Strong mathematical and analytical foundation Production-aware AI/ML integration System-level thinking (latency, throughput, scalability) Clear documentation and reproducible workflows 𝗖𝗼𝗿𝗲 𝗖𝗮𝗽𝗮𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀: WebRTC / LiveKit Engineering SFU scaling strategies, TURN/STUN configuration, ICE tuning Optimizing jitter, packet loss, simulcast/SVC, bitrate adaptation Debugging join failures, audio/video inconsistencies, device issues 𝗠𝗲𝗱𝗶𝗮 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀: FFmpeg and OBS workflows for ingest → process → record → distribute Reliable multi-track recording and egress configurations Low-latency transcoding and optimized CPU/GPU usage 𝗜𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝘃𝗲 & 𝟯𝗗 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴: Unity, Unreal and Omniverse real-time streaming setups Digital twin + avatar pipelines with synchronized audio/video Ultra-low-latency input → render → stream loops 𝗔𝗜/𝗠𝗟 & 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻: Real-time OCR, text extraction, scene understanding Background removal, segmentation, enhancement Avatar/lip-sync triggers, real-time CV analytics ML inference integrated into WebRTC with strict latency control 𝗗𝗲𝘃𝗢𝗽𝘀 & 𝗢𝗯𝘀𝗲𝗿𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆: Dockerized deployments, environment separation Monitoring (jitter, RTT, CPU/mem, packet loss, TURN usage) Alerting, runbooks, load testing, failure-mode analysis 𝗖𝗼𝗿𝗲 𝗖𝗮𝗽𝗮𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀: WebRTC / LiveKit Engineering Media Pipelines Interactive & 3D Streaming AI/ML & Computer Vision DevOps & Observability 𝗠𝘆 𝗺𝗶𝘀𝘀𝗶𝗼𝗻: To create next-generation communication systems by merging AI/ML, signal processing and automation and to invent efficient algorithmic approaches that solve complex real-world challenges. Need a solid solution? Drop a text anytime