We are a fast-growing startup on a mission to revolutionize the logistics industry by building an Open Parcel Network. Our ML-driven platform leverages predictive models, optimization algorithms, and deep learning to transform parcel delivery operations. We are seeking a hands-on Machine Learning Engineer to build, deploy, and scale ML models that drive real-world operational excellence.
:
As a Machine Learning Engineer, you will design, develop, and deploy production-grade machine learning systems that optimize logistics operations at scale. You will work on predictive modeling, optimization algorithms, computer vision, time series forecasting, and recommendation systems. This role requires strong expertise in classical ML, deep learning, MLOps practices, and the ability to build robust, scalable ML infrastructure in a fast-paced startup environment.
Key Responsibilities:
Model Development & Training:
Design and develop machine learning models for logistics optimization including demand forecasting, route optimization, delivery time prediction, anomaly detection, and resource allocation. Train models using classical ML algorithms, deep learning, and ensemble methods.
Feature Engineering:
Perform sophisticated feature engineering from raw data including temporal features, geospatial features, and domain-specific transformations. Build automated feature pipelines that ensure data quality and feature consistency.
Model Experimentation & Evaluation:
Conduct rigorous experimentation using proper train/validation/test splits, cross-validation, and A/B testing. Evaluate models using appropriate metrics and statistical tests. Track experiments systematically using MLflow, Weights & Biases, or similar tools.
Production Deployment:
Deploy ML models to production environments with proper versioning, monitoring, and rollback capabilities. Build scalable inference pipelines that handle real-time and batch predictions with low latency and high throughput.
MLOps & Infrastructure:
Build and maintain ML infrastructure including training pipelines, model registries, feature stores, and serving infrastructure. Implement CI/CD for ML, automated retraining, and model monitoring systems.
Model Optimization:
Optimize models for production including hyperparameter tuning, model compression, quantization, and inference optimization. Balance model performance with computational efficiency and cost.
Data Pipeline Development:
Work with data engineers to build robust data pipelines that preprocess, validate, and transform data for ML training and inference. Ensure data quality and handle data drift.
Monitoring & Maintenance:
Implement comprehensive model monitoring including performance metrics, data drift detection, model degradation alerts, and automated retraining triggers. Debug and resolve production issues.
Collaboration:
Partner with data scientists to productionize research models, work with platform engineers on infrastructure, and collaborate with product teams to understand business requirements and translate them into ML solutions.
Research & Innovation:
Stay current with latest ML research and techniques. Experiment with new algorithms, architectures, and approaches. Evaluate when to adopt cutting-edge techniques versus proven methods.
Qualifications:
Education:
Bachelor's or Master's degree in Computer Science, Machine Learning, Data Science, Mathematics, Statistics, Engineering, or a related quantitative field. Ph.D. is a plus but not required.
Experience:
3-5 years of experience in machine learning engineering or related field, with proven track record of deploying ML models to production and delivering measurable business impact.
Technical Expertise:
Strong programming skills in Python with production-quality code practices. Experience with software engineering principles including testing, version control, and code review.
Deep expertise in ML frameworks and libraries: scikit-learn for classical ML, PyTorch or TensorFlow for deep learning, XGBoost/LightGBM/CatBoost for gradient boosting.
Solid understanding of ML fundamentals including supervised/unsupervised learning, regularization, cross-validation, bias-variance tradeoff, and evaluation metrics.
Experience with deep learning architectures (CNNs, RNNs, Transformers) and their applications in computer vision, NLP, or time series.
Proficiency in data processing and analysis: pandas, NumPy, SQL, and working with large datasets. Experience with distributed computing (Spark, Dask) is a plus.
Hands-on experience with MLOps tools and practices: MLflow, Kubeflow, or similar platforms for experiment tracking, model registry, and deployment.
Strong knowledge of cloud-based solutions (SageMaker, Vertex AI, Azure ML).
Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes) for ML workloads.
Familiarity with feature stores (Feast, Tecton) and data versioning tools (DVC, Pachyderm).
Understanding of model monitoring, observability, and debugging techniques for production ML systems.
Experience with optimization techniques: hyperparameter tuning (Optuna, Ray Tune), model compression, and inference optimization.
Bonus: Experience with specific ML domains relevant to logistics (time series forecasting, optimization algorithms, geospatial ML, recommendation systems).
Statistical & Mathematical Foundation:
Strong understanding of statistics, probability, linear algebra, and optimization. Ability to reason about model behavior from first principles.
Problem-Solving:
Excellent analytical and debugging skills. Ability to troubleshoot complex issues in ML pipelines, data quality, model performance, and production systems.
Pragmatism:
Understand when to use simple vs. complex solutions. Balance model accuracy with engineering constraints like latency, cost, and maintainability.
Communication:
Strong communication skills with ability to explain technical ML concepts to diverse audiences including engineers, data scientists, and business stakeholders.
Ownership:
Take end-to-end ownership of ML projects from problem definition through deployment and monitoring. Drive projects to completion with minimal supervision.
Why Join Us?
Work on impactful ML problems that optimize real-world logistics operations at scale.
Build production ML systems from the ground up with modern tools and best practices.
Join a dynamic startup where you can shape ML infrastructure and engineering culture.
Collaborate with talented data scientists, engineers, and domain experts passionate about solving hard problems.
Own significant projects and see the direct impact of your models on business metrics.
Continuous learning opportunities with access to courses, conferences, and research papers.
Work with diverse ML problems: forecasting, optimization, computer vision, anomaly detection, and more.
How to Apply:
If you are a skilled Machine Learning Engineer passionate about building production ML systems that drive real business value, we want to hear from you. Please submit your resume and a cover letter detailing your ML engineering experience, notable models you've deployed to production, and why you're excited about transforming logistics through machine learning.
Job Type: Full-time
Pay: ₹1,200,000.00 - ₹1,800,000.00 per year
Benefits:
Paid time off
Work from home
Work Location: Remote
Beware of fraud agents! do not pay money to get a job
MNCJobsIndia.com will not be responsible for any payment made to a third-party. All Terms of Use are applicable.