Senior AI Scientist (Vision Lead)

ACURA SOLUTIONS LTD; Mumbai; On-site; INR 1,500,000 - 3,000,000; Full time

Job summary

ACURA SOLUTIONS LTD in Mumbai is looking for a Sr. AI Scientist to develop and scale a Vision AI Center of Excellence. You will build production-grade spatial analytics that drive revenue in heavy industries such as ports and logistics.

The ideal candidate has substantial experience in deploying computer vision models, expertise in frameworks like PyTorch and OpenCV, and experience with YOLO variants. Join us to turn cutting-edge technology into impactful solutions.

Qualifications

• 35 years of hands-on experience deploying computer vision models into real-world production environments.
• Deep expertise in PyTorch, OpenCV, and Hugging Face.
• Proven experience with YOLO variants and tracking algorithms.

Responsibilities

• Advance our YOLO pipeline from single-frame detection to multi-object tracking.
• Adapt and optimize Vision-Language Models for industry-specific tasks.
• Compress models for efficient deployment on edge nodes.
• Build automated data curation and synthetic data generation loops.

Skills

Computer vision deployment

Experience with PyTorch

Deep expertise in OpenCV

Familiarity with Hugging Face ecosystem

Proven experience with YOLO variants

Tracking algorithms like ByteTrack/DeepSORT

Comfortable working in Ubuntu

Job description

We are looking for a Sr. AI Scientist to own and scale our Vision AI Center of Excellence (COE). You aren't joining a research lab to write theoretical papers; you are here to build production‑grade, real‑time spatial analytics that drive immediate revenue in heavy industries like ports, logistics, and manufacturing. You will take our working Ubuntu CPU‑based Edge relay software (YOLO + RTSP/RTMP encoding) and turn it into an enterprise‑grade live video analytics platform. You will work alongside our Platform team to deploy models directly into turnkey Edge NVR hardware boxes and air‑gapped environments.

Core Responsibilities

• Spatio‑Temporal Pipeline Engineering: Advance our current YOLO pipeline from single‑frame object detection to multi‑object tracking (MOT) across space and time for vehicle tracking, worker safety compliance, and people analytics.
• VLM Fine‑Tuning & Quantization: Adapt, fine‑tune, and optimize state‑of‑the‑art open‑weight Vision‑Language Models (e.g., Qwen2.5‑VL/Qwen3‑VL, LLaVA, SAM) for highly localized, industry‑specific tasks.
• Edge Optimization: Work closely with MLOps to compress models using quantization frameworks (AWQ, GPTQ) so complex tracking and safety logic can run efficiently on NVR boxes and CPU/NPU edge nodes.
• Synthetic Data Pipelines: Build automated data curation and synthetic data generation loops to handle poor lighting, rusted container codes, and unique industrial edge cases.

Required Technical Skillset

• Experience: 35 years of hands‑on experience deploying computer vision models into real‑world production environments.
• Frameworks: Deep expertise in PyTorch, OpenCV, and the Hugging Face ecosystem.
• Tracking & Detection: Proven experience with YOLO variants, combined with tracking algorithms like ByteTrack, DeepSORT, or StrongSORT.
• Quantization & Serving: Familiarity with Triton Inference Server, vLLM, TensorRT‑LLM, and ONNX Runtime.
• Infrastructure: Comfortable working in Ubuntu environments, handling RTSP/RTMP video streams, and collaborating within Docker/containerized workflows.

This job is provided by Shine.com