Role & responsibilities

Job Title: Lip Sync Engineer (Python | React | AWS)

Job Summary

We are seeking a highly skilled Lip Sync Engineer to design, develop, and optimize AI-powered lip synchronization solutions for avatar-based video generation. The ideal candidate should have strong expertise in Python, React, and AWS, along with hands-on experience in deep learning-based video generation, audio processing, and real-time inference pipelines. You will be responsible for building scalable applications that synchronize avatar lip movements with AI-generated speech while ensuring high performance and low latency.

Key Responsibilities

- Design, develop, and optimize AI-driven lip synchronization solutions for avatar-based video generation.
- Build and enhance lip sync pipelines using Python and open-source models such as Wav2Lip or similar technologies.
- Develop responsive frontend interfaces using React for avatar interaction and video generation workflows.
- Integrate text-to-speech (TTS) platforms such as ElevenLabs, Piper, or equivalent with lip sync pipelines.
- Develop APIs using Python frameworks such as FastAPI or Flask to support real-time video generation services.
- Deploy and manage AI inference workloads on AWS (EC2, GPU instances, S3, Lambda, CloudFront, API Gateway, etc.).
- Optimize deep learning models for low-latency, near real-time inference (approximately 13 seconds).
- Work with GPU acceleration technologies (CUDA) to improve inference performance.
- Build scalable backend services and integrate frontend applications with AI pipelines.
- Collaborate with AI engineers, product teams, and clients to gather requirements and deliver high-quality solutions.
- Monitor, troubleshoot,



and continuously improve model accuracy, performance, and scalability.

Mandatory Skills

- Solid programming experience in Python.
- Hands-on experience with React.js.
- Experience with AWS services such as EC2, S3, Lambda, API Gateway, CloudFront, and GPU-based deployments.
- Experience with Python frameworks such as FastAPI or Flask.
- Strong understanding of REST APIs and backend service development.
- Experience with deep learning frameworks such as PyTorch.
- Hands-on experience with open-source lip sync technologies such as Wav2Lip or equivalent.
- Experience integrating TTS platforms such as ElevenLabs or similar.
- Knowledge of video processing, audio processing, and multimedia pipelines.
- Familiarity with Docker, Git, and Linux environments.

Preferred Skills

- Experience with Hugging Face models and pipelines.
- Knowledge of LangChain or AI orchestration frameworks.
- Experience with CUDA and GPU optimization.
- Familiarity with FFmpeg and video processing workflows.
- Experience with Kubernetes and container orchestration.
- Knowledge of C++ for performance optimization.
- Experience building real-time AI inference pipelines.
- Exposure to avatar-based AI applications or generative AI products.

Qualifications

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
- 4+ years of software development experience with strong expertise in Python.
- Hands-on experience in AI/ML-based video or audio processing solutions.
- Strong problem-solving skills and the ability to work in a fast-paced Agile environment.
- Excellent communication and stakeholder collaboration skills.

Preferred candidate profile

📌 Artificial Intelligence Engineer (Bengaluru)
🏢 Talent21
📍 Bengaluru