Job Summary
Role and Responsibilities:
- Lead the AI analytics team including Computer Vision Engineers and QA testers.
- Design and implement efficient deployment pipelines for multiple AI models (face recognition, object detection, behavior recognition, etc.) across 12+ CCTV streams.
- Architect containerized environments (Docker, Kubernetes, etc.) for scalable AI model deployment.
- Optimize inference performance on high-end GPU workstations (e.g., NVIDIA RTX 4090) and edge devices (Jetson, Xavier, etc.).
- Monitor, test, and debug deployed models using tools like Prometheus, Grafana, or custom dashboards.
- Collaborate with the VMS integration team to ensure seamless flow of processed video streams and inference results into the central system.
- Develop robust APIs or use frameworks such as GStreamer, FastAPI, or NVIDIA DeepStream for real-time integration.
- Conduct stress and performance testing to maintain consistent operation during peak load.
- Coordinate with data engineers (merged with CV team) for preprocessing, labeling, and versioning of datasets.
- Ensure all deployments are compliant with security, privacy, and access control protocols.
- Maintain documentation of deployment procedures, architecture diagrams, and version control of models.
Required Skills
Skills and Qualification:
Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or related technical discipline.
Experience:
- 3+ years of experience in AI model deployment or ML Ops.
- At least 1 year in a leadership or senior engineer capacity.
- Demonstrated experience deploying computer vision models in production environments (preferably for surveillance or security domains).
- Experience in real-time video processing using OpenCV, TensorRT, DeepStream, or similar frameworks.
Certifications (Preferred):
- NVIDIA Certified Deep Learning Institute credentials
- Google Cloud/AWS ML Engineer certifications
- Docker & Kubernetes certifications
- ML Ops or DevOps relevant certificates
Skills:
- Expertise in containerization and orchestration (Docker, Docker Compose, Kubernetes).
- Proficiency with Python, Bash scripting, and AI frameworks (TensorFlow, PyTorch, ONNX).
- Deep understanding of GPU optimization, memory profiling, and inference acceleration.
- Familiarity with deployment tools (TorchServe, Triton Inference Server, etc.).
- Experience with CI/CD pipelines for AI workflows (GitLab CI, Jenkins, etc.).
- Knowledge of GStreamer, RTSP, and handling real-time video feeds.
Desired Personal Qualities:
- Proven leadership and team mentoring capabilities.
- Analytical and solution-oriented mindset with strong troubleshooting skills.
- Ability to manage multiple priorities in a fast-paced environment.
- Excellent communication skills to interface with both technical and non-technical stakeholders.
- Ownership-driven with a commitment to delivery excellence.
Additional Notes
Candidates who applied earlier for the same position may not apply again. Their application submitted earlier will be included in the selection process.
