Software Engineer – AI/ML

Job Description: Software Engineer – AI/ML (Demand Forecasting & Inventory Optimization)About the Role

We are seeking an experienced Software Engineer (AI/ML) with a strong background in end-to-end data and machine learning pipeline development. The candidate will be responsible for designing, developing, and deploying scalable AI/ML solutions for demand forecasting and inventory optimization in the pharmacy retail domain.

This is a hands-on individual contributor role requiring full ownership of the AI/ML lifecycle – from data ingestion and preprocessing to model development, deployment, monitoring, and optimization.

Key Responsibilities

·     Data Engineering & Management

·     Build and manage robust ETL/ELT pipelines for structured and unstructured data (sales, inventory, supplier data, etc.).

·     Implement data versioning and lineage tracking using DVC or similar tools.

·     Ensure data quality, consistency, and security across sources.

·     Machine Learning Development

·     Develop, train, and validate time-series forecasting models (ARIMA, Prophet, LSTM, Transformer-based models, etc.) tailored for pharmacy demand forecasting.

·     Design ML models for inventory optimization (stock levels, reorder points, expiry risk, etc.).

·     Implement feature engineering, hyperparameter tuning, and model performance monitoring.

·     ML Operations (MLOps)

·     Set up and manage experiment tracking, model registry, and reproducibility using MLflow or DVC.

·     Automate training and deployment workflows using Prefect, Airflow, or similar orchestration tools.

·     Deploy ML models as REST APIs using FastAPI and integrate with pharmacy retail systems.

·     Containerize solutions with Docker and deploy on AWS Cloud (ECS, Lambda, S3, SageMaker, or EKS as needed).

·     System & Project Ownership

·     Manage end-to-end ML lifecycle independently with minimal supervision.

·     Collaborate with product and business teams to align technical solutions with business needs.

·     Continuously monitor models in production for data drift, performance degradation, and retraining needs.

Key Skills & Qualifications

·     Education: Bachelor's/Master's degree in Computer Science, Data Science, or related field.

·     Experience: Minimum 5 years of hands-on experience in software engineering and ML pipeline development.

Technical Skills

·     Programming: Strong in Python (pandas, NumPy, scikit-learn, PyTorch/TensorFlow).

·     Version Control: Git, GitHub/GitLab.

·     Data & ML Pipeline Tools: DVC, MLflow, Prefect (or Airflow).

·     APIs & Microservices: FastAPI, RESTful API design.

·     Cloud Platforms: AWS (S3, ECS/EKS, Lambda, SageMaker, RDS).

·     Containerization: Docker, basic Kubernetes (optional but preferred).

·     Databases: SQL (PostgreSQL, MySQL), NoSQL (MongoDB, DynamoDB).

·     CI/CD: Experience with CI/CD pipelines for ML model deployment.

·     Monitoring: ML monitoring and logging frameworks.

Domain & Analytical Skills

·     Experience with time-series forecasting and optimization techniques.

·     Understanding of inventory and supply chain concepts (safety stock, lead time, reorder point).

·     Strong ability to translate business requirements into ML solutions.

Other Skills

·     Excellent problem-solving and analytical skills.

·     Strong communication and documentation abilities.

·     Ability to work independently and own complete ML solutions.

·     Exposure to Agile methodologies.