Senior ML/AI Engineer

Project description

About the Role

You will lead the design, development, and deployment of real-time video analytics systems for physical security. You will combine classical computer vision pipelines with large language models (LLMs) and vision-language models (VLMs) to enable natural-language scene querying, automated incident narration, operator alert summarization, and open-vocabulary detection—while meeting the latency, uptime, and compliance demands of 24/7 security operations.

Key Responsibilities

• Architect multi-camera NVIDIA DeepStream (GStreamer) pipelines for concurrent 4K/HD feeds with hardware-accelerated decode.
• Train and fine-tune detection, re-identification, and tracking models for security scenarios (low light, occlusion, fisheye).
• Integrate VLMs (e.g., Gemini Vision, Qwen-VL) for open-vocabulary queries, scene understanding, and anomaly explanation.
• Build LLM-powered operator workflows: natural-language alert search, incident summarization, and automated report generation.
• Optimize CV inference with TensorRT (INT8/FP16); manage LLM inference via Triton, vLLM, or equivalent serving for latency-sensitive paths.
• Design hybrid pipelines: fast CV models for real-time detection plus asynchronous LLM/VLM reasoning and narrative generation.
• Integrate with VMS platforms (Milestone, Genetec, Nx Witness) and ONVIF/RTSP camera APIs.
• Own production readiness: monitoring, model drift detection, prompt/version management, and retraining pipelines.

Required Skills & Experience

• NVIDIA & Inference Stack
• LLM & VLM Integration
• Computer Vision Domains (Surveillance)
• Video Pipeline & Integration
• Engineering & MLOps

Preferred / Nice-to-Have

• Deployments in critical infrastructure (airports, transport hubs, data centers, stadiums).
• Experience with NVIDIA Metropolis platform or partner ecosystem.
• Fisheye dewarping and PTZ auto-tracking.
• Night-vision / thermal camera fusion.
• False-alarm suppression at scale (10k+ camera networks).
• Privacy and compliance exposure (e.g., GDPR, CCPA, NDAA 889) in video systems.
• Knowledge of IEC 62676 and/or PSIA standards.