SiteRecon.ai
Website:
siterecon.ai
Job details:
Title: Computer Vision Software Engineer, Applied ML Operations
Industry: Computer Software
Employment Type: Full Time
Location: Remote(Preference for candidates in NCR)
About SiteRecon:
SiteRecon is on a mission to revolutionize the way businesses make decisions in North America by helping enterprise customers scale their sales teams. We automate property mapping and site visits through our innovative mapping platform, designed specifically for property maintenance contractors. By streamlining these processes, we give our clients back valuable time, accelerate their sales efforts, and enhance their profitability. Join us in building the next-generation property intelligence platform!
To learn more about what we do for our customers - https://order.siterecon.ai
About the Founders and the Team:
Founded by former IIT Delhi alumni with extensive experience in satellite imaging, eCommerce, and edtech. Our team is passionate about driving change in the industry.
Meet our team - https://www.linkedin.com/company/siterecon/people
About the Product:
SiteRecon combines the power of Amazon and Google Docs for maps, allowing users to easily create customized maps through our AI-driven data delivery system. This platform serves as a foundation for creating survey notes, operational plans, cost estimates, and more.
Market Overview:
Our primary focus is the landscaping industry in the United States, Canada, and Australia, which collectively represents a staggering $200 billion market.
Responsibilities:
● This role is not suitable for absolute freshers or candidates with only coursework/Kaggle exposure.
● 1.5 to 3 years of hands-on ML/CV engineering experience, with strong Python software skills and practical experience running models, managing datasets,debugging pipelines, and maintaining ML workflows.
● Must have trained, fine-tuned, or evaluated ML/CV models on real datasets.
● Must be comfortable reading, modifying, and debugging existing PyTorch code
● Should be able to build and maintain scripts for data processing, training, inference, evaluation, and reporting.
● Should understand datasets, labels, metrics, failure cases, and experiment tracking.
● Should be comfortable with Git, Linux, CLI, environments, configs, and basic cloud/GPU workflows.
Must-Have Skills:
● Strong Python
● PyTorch basics
● Computer vision fundamentals
● Dataset preparation and data wrangling
● Model training and evaluation
● Git, Linux, CLI
● Debugging mindset
● Clear experiment notes
● Ability to implement practical ideas from papers or open-source code
Nice-to-Have :
● CNNs, ViTs, transformers, U-Net, DeepLab, YOLO, SAM, or similar models
● Semantic segmentation or object detection experience
● Active learning workflows at scale
● High-resolution image processing
● Image tiling, cropping, stitching, or patch-based inference
● Docker/cloud GPU workflows
● Weights & Biases, MLflow, or TensorBoard
Core Responsibilities:
● Run and evaluate computer vision models on multi-class image datasets.
● Manage inference pipelines to scale datasets.
● Work with segmentation, detection, and classification models using CNN, ViT, and transformer-based architectures.
● Train, fine-tune, and compare pretrained models on internal datasets.
● Implement practical ideas from research papers, open-source repos, and technical references.
● Test new architectures, losses, augmentations, sampling strategies, and training techniques.
● Prepare, clean, version, and scale datasets for training, validation, and testing.
● Support active learning workflows: find uncertain samples, review failure cases, and prepare annotation batches.
● Track metrics, model versions, dataset versions, regressions, and experiment settings.
● Maintain Python pipelines for training, inference, evaluation, visualization, and reporting.
● Debug issues related to data quality, labels, class imbalance, image resolution, tiling, and model performance.
● Work closely with senior CV engineers and learn missing tools quickly.
Click on Apply to know more.