AI ML Senior Engineer

RMSI Cropalytics is seeking a highly skilled Senior ML / AI Engineer with strong expertise in machine learning, statistical modelling, and applied AI for agriculture and geospatial analytics. The candidate will be responsible for designing, developing, training, fine-tuning, and deploying ML/AI models for crop forecasting, satellite image analysis, crop-stage classification, disease detection, and document intelligence.

Key Responsibilities

• Understand business and analytical requirements and translate them into scalable ML/AI solutions
• Design, implement, and optimize machine learning and deep learning models from concept to production
• Develop end-to-end ML pipelines, including data ingestion, preprocessing, feature engineering, training, validation, and deployment
• Fine-tune hyperparameters and optimize model performance using statistical and mathematical techniques
• Work extensively with satellite imagery (optical & SAR) for crop health, yield estimation, and disease detection
• Build forecasting models for crop yield, acreage estimation, weather impact, and time-series analysis
• Develop ML-based solutions for PDF/document parsing, OCR, and text extraction
• Deploy models on AWS/GCP using managed ML services and MLOps best practices
• Collaborate with data engineers, GIS experts, and domain specialists

Required Technical Skills

Programming & Core Libraries

• Expert-level programming in Python
• Strong hands-on experience with:
1. NumPy, Pandas, SciPy
2. Scikit-learn
3. Matplotlib, Seaborn, Plotly
4. Statsmodels

Machine Learning & Deep Learning Frameworks

• TensorFlow / Keras
• PyTorch
• AWS SageMaker (BlazingText, XGBoost, built-in algorithms)
• Hugging Face Transformers
• ONNX (model optimization and portability)

Must-Have Experience in Forecasting & Time-Series Models (Agriculture & Climate)

• ARIMA / SARIMA
• LSTM / GRU
• Temporal CNN
• Transformer-based time-series models
• XGBoost / LightGBM for yield prediction
• Prophet

Crop Classification, Stage Detection & Yield Estimation Models

• Random Forest
• Gradient Boosting (XGBoost, LightGBM, CatBoost)
• Support Vector Machines (SVM)
• CNN-based classifiers
• U-Net / SegNet for crop segmentation
• NDVI/EVI-based feature modeling

Crop Disease & Stress Detection (Satellite & UAV Imagery)

• CNN architectures:
• ResNet, EfficientNet, DenseNet, MobileNet
• Vision Transformers (ViT, Swin Transformer)
• Object detection:
• YOLO (v5/v8)
• Faster R-CNN
• Semantic segmentation:
• U-Net, DeepLabV3+

Text, Document & OCR Intelligence

• NLP models:
• BERT, RoBERTa, DistilBERT
• Word2Vec, FastText
• OCR & document parsing:
• Tesseract OCR
• Amazon Textract
• LayoutLM
• PDF parsing & text extraction pipelines

Geospatial & Remote Sensing Tools (Strongly Preferred)

• GDAL, Rasterio
• GeoPandas
• QGIS / ArcGIS
• Google Earth Engine
• Experience with Sentinel, Landsat, Planet, MODIS data

Soft Skills

• Strong analytical and problem-solving abilities
• Excellent communication and documentation skills
• Ability to work independently and collaboratively in cross-functional teams
• Experience mentoring and training team members