Lip Sync Engineer

Job description

Lip Sync Engineer **Experience:** 57 Years **Location:** Bangalore, Hyderabad, Mumbai, Pune, Chennai **Qualification:** B.E / B.Tech / MCA Job Description We are seeking a highly skilled **Lip Sync Engineer** to design, develop, and optimize AI-driven lip synchronization solutions for avatar-based video generation. The ideal candidate will have hands-on experience with open-source lip sync technologies and be capable of delivering near real-time lip synchronization aligned with generated audio. Key Responsibilities - Develop and enhance lip synchronization systems for AI-generated avatars. - Implement solutions that synchronize avatar lip movements with audio within 1–3 seconds latency. - Work with and improve open-source frameworks such as Wav2Lip or similar models. - Integrate lip sync pipelines with Text-to-Speech (TTS) platforms such as ElevenLabs or equivalent. - Build and optimize avatar-based video generation workflows where static images are animated to speak. - Define and implement scalable compute infrastructure using AWS services such as EC2 and GPU instances. - Optimize models and pipelines for performance, latency, and output quality. - Collaborate directly with clients and cross-functional teams to understand requirements and deliver effective solutions. - Troubleshoot and improve AI inference pipelines for real-time or near real-time processing. Required Skills - Strong programming expertise in Python. - Hands-on experience with FastAPI and PyTorch. - Experience working with deep learning-based video and audio synthesis models. - Proven experience with lip sync technologies such as Wav2Lip or similar frameworks. - Experience integrating audio pipelines and TTS systems. - Familiarity with GPU acceleration and CUDA. - Strong understanding of Machine Learning, Deep Learning, and Computer Vision concepts. Preferred Skills - Experience with Hugging Face models and pipelines. - Knowledge of Piper or other Text-to-Speech engines. - Exposure to C++ for performance optimization. - Experience building real-time or near real-time ML inference pipelines. - Prior experience in avatar AI, talking-head generation, or AI video applications. - Experience working with AWS GPU infrastructure. **Mandatory Skills** Python, PyTorch, FastAPI, Wav2Lip, Deep Learning, Audio/Video Synthesis, Machine Learning, Computer Vision, CUDA, AWS GPU Infrastructure, TTS Integration.