Computer Vision Engineer

The vacancy has been archived and is no longer active

Main requirements

Requirements

Commercial experience in Computer Vision and Video Analytics.
Practical experience with RTSP, DeepStream, GStreamer, TensorRT.
Excellent knowledge of PyTorch, OpenCV, YOLO.
Experience in model optimization (ONNX, TensorRT, OpenVINO, CUDA).
Understanding modern Vision Transformers (ViT, DETR, Swin, TimeSformer, ViViT) and multimodal models (LLaVA, Qwen-VL).
Experience working with LLM, RAG and agent systems will be an advantage.
Experience in the development of production AI systems and ML services.

DeepStream SDK.
CUDA.
Triton Inference Server.
Kafka.
Kubernetes.
LangGraph.
vLLM.
MLflow.

What you will do

We are developing a large-scale video monitoring and intelligent video analytics system for a government project. We are looking for an engineer who will design and implement AI solutions for processing video streams in real time.

Main tasks

Development of production video analytics systems based on Computer Vision.
Processing dozens and hundreds of RTSP video streams with minimal delay.
Building and optimizing pipelines on NVIDIA DeepStream, GStreamer and TensorRT.
Development and implementation of Computer Vision models (YOLO, ViT, Video Transformers, VLM).
Optimization of inference on GPU/CPU (TensorRT, OpenVINO, ONNX, Quantization).
Integration of Computer Vision with LLM and multimodal models to generate intelligent video data analytics.
Development of AI services on FastAPI/gRPC, Docker, Kubernetes.
Building RAG and Agentic AI solutions (LangGraph, vLLM, Function Calling).
Designing the architecture of AI components and participating in technical decision-making.