Senior ML/AI Engineer

WeAgile Software Solutions Pvt. Ltd.; Pune District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

WeAgile Software Solution Pvt. Ltd.

seeks a seasoned specialist to lead the design, development and deployment of real-time video analytics systems for physical security, blending classical CV pipelines with LLMs and VLMs to enable natural-language scene queries and automated incident narration. You will combine traditional computer-vision pipelines with large language models and vision-language models to enable natural-language scene querying and automated incident narration.

Qualifications

• NVIDIA inference stack expertise for real-time CV/AI deployments.
• Experience integrating LLMs and VLMs with vision systems.

Responsibilities

• Architect multi-camera NVIDIA DeepStream 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.

Skills

NVIDIA inference stack

LLM/VLM integration

Job description

About WeAgile Software Solution Pvt. Ltd.:

We are a leading technology firm that integrates strategy, design, and software engineering to enable enterprises and technology disruptors across the globe to thrive as modern digital businesses. Ongoing digital disruption is challenging enterprises to keep pace with the accelerating rate of technological change. This is where WeAgile can help. We leverage our vast experience to improve our clients' ability to respond to change; utilize data assets to unlock new sources of value; create adaptable technology platforms that move with business strategies; and rapidly design, deliver, and evolve exceptional digital products and experiences at scale.

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

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.
• Privacy and compliance exposure (e.g., GDPR, CCPA, NDAA 889) in video systems.
• Knowledge of IEC 62676 and/or PSIA standards.