Computer Vision Engineer

About Company,Droisys is an innovation technology company focused on helping companies accelerate their digital initiatives from strategy and planning through execution. We leverage deep technical expertise, Agile methodologies, and data-driven intelligence to modernize systems of engagement and simplify human/tech interaction. Amazing things happen when we work in environments where everyone feels a true sense of belonging and when candidates have the requisite skills and opportunities to succeed. At Droisys, we invest in our talent and support career growth, and we are always on the lookout for amazing talent who can contribute to our growth by delivering top results for our clients. Join us to challenge yourself and accomplish work that matters.Here's the job details,Computer Vision Engineer Gurugram, HaryanaAbout the RoleExperience: 3–6 yearsWe are seeking aComputer Vision Software engineerwith a strong foundation inmachine learning, real-time vision systems, and edge deployment optimization . The ideal candidate will bring5+ years of experiencein architecting scalable, production-grade CV solutions with a deep understanding ofimage segmentation, object classification, and model acceleration techniques . This role involvesdesigning end-to-end vision pipelinesthat operate inlow-latency, constrained environments , and buildingrobust perception systemsforobject interaction and classification tasks in structured visual environments .Key Responsibilities Model Development & Optimization Implement deep learning models forobject detection, instance segmentation, and classificationin structured visual domains. Develop and optimize models forreal-time inferenceonedge devicesusing tools likeTensorRT ,ONNX ,NVIDIA Jetson , andCUDA . Apply advanced techniques formodel compression ,quantization , andpruningto meet performance constraints. System Architecture Design and own the entirecomputer vision pipeline : fromcamera capture to final inference output . Ensurelow-latency performance , particularly onembedded or GPU-powered edge hardware . Benchmark and profile model performance using tools likeNVIDIA Nsight ,trtexec , orcustom profilers . Data Engineering & Image Processing Drive dataset curation, augmentation, and labeling strategies for diverse object classes. Develop efficientpreprocessing and postprocessing pipelines , including noise reduction, image enhancement, and perspective correction. Deployment & Productionization Integrate models into production environments with CI/CD andML Ops pipelines . Ensure secure, efficient, and fault-tolerant deployment of models on embedded systems or cloud-edge hybrids. Research & Innovation Stay current with the latest trends indeep learning ,vision transformers ,diffusion models , andreal-time inference . Evaluate research papers and contribute to internal innovation throughPOCs and rapid prototyping .Required Skills & Experience 5+ yearsof industry experience incomputer vision and machine learning. Expert inPython , with strong experience inOpenCV ,PyTorch , and/orTensorFlow . Strong grasp ofdeep learning concepts : CNNs, attention mechanisms, image segmentation, small-object detection. In-depth knowledge ofimage processing , perspective warping, homography, and visual tracking. Hands-on experience withmodel optimization and deploymentusingTensorRT ,ONNX ,CUDA , andJetson platforms . Proficient in tools likeDocker ,Git , andMLFlowor other model tracking/versioning frameworks. Solid foundation inlinear algebra, calculus, probability, and statistics . Demonstrated experience in buildingCV systems for real-time applications , especially onedge hardware .Preferred Qualifications Prior experience developing perception systems for structured, rule-based environments (e.g., card games, tabletop detection, automated gameplay, etc.) Knowledge ofhardware-aware training ,mixed-precision inference , orvision transformers. Experience withC++/CUDA kernelsfor custom ops or performance enhancement. Published papers, patents, or open-source contributions in the CV/ML space.Soft Skills Strongproblem-solvingmindset and ability to work inambiguous, fast-pacedenvironments. Excellentcommunicationandtechnical documentationskills. Ability tomentorjunior engineers andcollaborateacross disciplines.Bonus Tools / Stack Exposure TensorRT, ONNX, Jetson Nano/Xavier, NVIDIA Nsight DeepStream SDK, OpenVINO FastAPI / Flask for exposing inference APIs GStreamer, FFmpeg for video pipeline optimization DVC, ClearML, or similar experiment tracking toolsDroisys is an equal opportunity employer. We do not discriminate based on race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law. Droisys believes in diversity, inclusion, and belonging, and we are committed to fostering a diverse work environment.