Machine Learning Engineer

Lead a team of data scientists from top tier schools and collaborate with Founders and business
heads to solve complex business problems
- Develop statistical, and machine learning-based models/pipelines/methods to improve business
processes and engagements
- Conduct sophisticated data mining analyses of large volumes of data and build data science
models, as required, as part of the credit and risk underwriting solutions; customer engagement and
retention; new business initiatives; business process improvements
- Translate data mining results into a clear business-focused deliverable for decisionmakers
- Working with Application Developers on integrating machine learning algorithms and data mining
models into operational systems so it could lead to automation, productivity increase, and time
savings
- Provide the technical direction required to resolve complex issues to ensure the on-time delivery of
solutions that meet the business team’s expectations. May need to develop new methods to apply
to situations
- Knowledge of how to leverage statistical models in algorithms is a must
- Experience in multivariate analysis; identifying how several parameters can affect
retention/behaviour of the customer and identifying actions at different points of the customer lifecycle

Extensive experience coding in Python and having mentored teams to learn the same
- Great understanding of the data science landscape and what tools to leverage for different
problems
- A great structured thinker that could bring structure to any data science problem quickly
- Ability to visualize data stories and adept in data visualization tools and present insights as cohesive
stories to senior leadership
- Excellent capability to organize large data sets collected from many sources (web APIs and internal
databases) to get actionable insights
- Initiate data science programs in the team and collaborate across other data science teams to build
a knowledge database

What you will do

• Bring in industry best practices around creating and maintaining robust data pipelines for complex data projects with/without AI component
  • programmatically ingesting data from several static and real-time sources (incl. web scraping)
  • rendering results through dynamic interfaces incl. web / mobile / dashboard with the ability to log usage and granular user feedbacks
  • performance tuning and optimal implementation of complex Python scripts (using SPARK), SQL (using stored procedures, HIVE), and NoSQL queries in a production environment

• Industrialize ML / DL solutions and deploy and manage production services; proactively handle data issues arising on live apps
• Perform ETL on large and complex datasets for AI applications - work closely with data scientists on performance optimization of large-scale ML/DL model training
• Build data tools to facilitate fast data cleaning and statistical analysis
• Ensure data architecture is secure and compliant
• Resolve issues escalated from Business and Functional areas on data quality, accuracy, and availability
• Work closely with APAC CDO and coordinate with a fully decentralized team across different locations in APAC and global HQ (Paris).

You should be

•  Expert in structured and unstructured data in traditional and Big data environments – Oracle / SQLserver, MongoDB, Hive / Pig, BigQuery, and Spark
• Have excellent knowledge of Python programming both in traditional and distributed models (PySpark)
• Expert in shell scripting and writing schedulers
• Hands-on experience with Cloud - deploying complex data solutions in hybrid cloud / on-premise environment both for data extraction/storage and computation
• Hands-on experience in deploying production apps using large volumes of data with state-of-the-art technologies like Dockers, Kubernetes, and Kafka
• Strong knowledge of data security best practices
• 5+ years experience in a data engineering role
• Science / Engineering graduate from a Tier-1 university in the country
• And most importantly, you must be a passionate coder who really cares about building apps that can help people do things better, smarter, and faster even when they sleep

• 3+ years of Experience majoring in applying AI/ML/ NLP / deep learning / data-driven statistical analysis & modelling solutions.
• Programming skills in Python, knowledge in Statistics.
• Hands-on experience developing supervised and unsupervised machine learning algorithms (regression, decision trees/random forest, neural networks, feature selection/reduction, clustering, parameter tuning, etc.). Familiarity with reinforcement learning is highly desirable.
• Experience in the financial domain and familiarity with financial models are highly desirable.
• Experience in image processing and computer vision.
• Experience working with building data pipelines.
• Good understanding of Data preparation, Model planning, Model training, Model validation, Model deployment and performance tuning.
• Should have hands on experience with some of these methods: Regression, Decision Trees,CART, Random Forest, Boosting, Evolutionary Programming, Neural Networks, Support Vector Machines, Ensemble Methods, Association Rules, Principal Component Analysis, Clustering, ArtificiAl Intelligence
• Should have experience in using larger data sets using Postgres Database. 

 

Company Profile
XressBees – a logistics company started in 2015 – is amongst the fastest growing companies of its sector. Our
vision to evolve into a strong full-service logistics organization reflects itself in the various lines of business like B2C
logistics 3PL, B2B Xpress, Hyperlocal and Cross border Logistics.
Our strong domain expertise and constant focus on innovation has helped us rapidly evolve as the most trusted
logistics partner of India. XB has progressively carved our way towards best-in-class technology platforms, an
extensive logistics network reach, and a seamless last mile management system.
While on this aggressive growth path, we seek to become the one-stop-shop for end-to-end logistics solutions. Our
big focus areas for the very near future include strengthening our presence as service providers of choice and
leveraging the power of technology to drive supply chain efficiencies.
Job Overview
XpressBees would enrich and scale its end-to-end logistics solutions at a high pace. This is a great opportunity to join
the team working on forming and delivering the operational strategy behind Artificial Intelligence / Machine Learning
and Data Engineering, leading projects and teams of AI Engineers collaborating with Data Scientists. In your role, you
will build high performance AI/ML solutions using groundbreaking AI/ML and BigData technologies. You will need to
understand business requirements and convert them to a solvable data science problem statement. You will be
involved in end to end AI/ML projects, starting from smaller scale POCs all the way to full scale ML pipelines in
production.
Seasoned AI/ML Engineers would own the implementation and productionzation of cutting-edge AI driven algorithmic
components for search, recommendation and insights to improve the efficiencies of the logistics supply chain and
serve the customer better.
You will apply innovative ML tools and concepts to deliver value to our teams and customers and make an impact to
the organization while solving challenging problems in the areas of AI, ML , Data Analytics and Computer Science.
Opportunities for application:
- Route Optimization
- Address / Geo-Coding Engine
- Anomaly detection, Computer Vision (e.g. loading / unloading)
- Fraud Detection (fake delivery attempts)
- Promise Recommendation Engine etc.
- Customer & Tech support solutions, e.g. chat bots.
- Breach detection / prediction
An Artificial Intelligence Engineer would apply himself/herself in the areas of -
- Deep Learning, NLP, Reinforcement Learning
- Machine Learning - Logistic Regression, Decision Trees, Random Forests, XGBoost, etc..
- Driving Optimization via LPs, MILPs, Stochastic Programs, and MDPs
- Operations Research, Supply Chain Optimization, and Data Analytics/Visualization
- Computer Vision and OCR technologies
The AI Engineering team enables internal teams to add AI capabilities to their Apps and Workflows easily via APIs
without needing to build AI expertise in each team – Decision Support, NLP, Computer Vision, for Public Clouds and
Enterprise in NLU, Vision and Conversational AI.Candidate is adept at working with large data sets to find
opportunities for product and process optimization and using models to test the effectiveness of different courses of
action. They must have knowledge using a variety of data mining/data analysis methods, using a variety of data tools,
building, and implementing models, using/creating algorithms, and creating/running simulations. They must be
comfortable working with a wide range of stakeholders and functional teams. The right candidate will have a passion
for discovering solutions hidden in large data sets and working with stakeholders to improve business outcomes.

Roles & Responsibilities
● Develop scalable infrastructure, including microservices and backend, that automates training and
deployment of ML models.
● Building cloud services in Decision Support (Anomaly Detection, Time series forecasting, Fraud detection,
Risk prevention, Predictive analytics), computer vision, natural language processing (NLP) and speech that
work out of the box.
● Brainstorm and Design various POCs using ML/DL/NLP solutions for new or existing enterprise problems.
● Work with fellow data scientists/SW engineers to build out other parts of the infrastructure, effectively
communicating your needs and understanding theirs and address external and internal shareholder's
product challenges.
● Build core of Artificial Intelligence and AI Services such as Decision Support, Vision, Speech, Text, NLP, NLU,
and others.
● Leverage Cloud technology –AWS, GCP, Azure
● Experiment with ML models in Python using machine learning libraries (Pytorch, Tensorflow), Big Data,
Hadoop, HBase, Spark, etc
● Work with stakeholders throughout the organization to identify opportunities for leveraging company data to
drive business solutions.
● Mine and analyze data from company databases to drive optimization and improvement of product
development, marketing techniques and business strategies.
● Assess the effectiveness and accuracy of new data sources and data gathering techniques.
● Develop custom data models and algorithms to apply to data sets.
● Use predictive modeling to increase and optimize customer experiences, supply chain metric and other
business outcomes.
● Develop company A/B testing framework and test model quality.
● Coordinate with different functional teams to implement models and monitor outcomes.
● Develop processes and tools to monitor and analyze model performance and data accuracy.
● Develop scalable infrastructure, including microservices and backend, that automates training and
deployment of ML models.
● Brainstorm and Design various POCs using ML/DL/NLP solutions for new or existing enterprise problems.
● Work with fellow data scientists/SW engineers to build out other parts of the infrastructure, effectively
communicating your needs and understanding theirs and address external and internal shareholder's
product challenges.
● Deliver machine learning and data science projects with data science techniques and associated libraries
such as AI/ ML or equivalent NLP (Natural Language Processing) packages. Such techniques include a good
to phenomenal understanding of statistical models, probabilistic algorithms, classification, clustering, deep
learning or related approaches as it applies to financial applications.
● The role will encourage you to learn a wide array of capabilities, toolsets and architectural patterns for
successful delivery.
What is required of you?
You will get an opportunity to build and operate a suite of massive scale, integrated data/ML platforms in a broadly
distributed, multi-tenant cloud environment.
● B.S., M.S., or Ph.D. in Computer Science, Computer Engineering
● Coding knowledge and experience with several languages: C, C++, Java,JavaScript, etc.
● Experience with building high-performance, resilient, scalable, and well-engineered systems
● Experience in CI/CD and development best practices, instrumentation, logging systems
● Experience using statistical computer languages (R, Python, SLQ, etc.) to manipulate data and draw insights
from large data sets.
● Experience working with and creating data architectures.
● Good understanding of various machine learning and natural language processing technologies, such as
classification, information retrieval, clustering, knowledge graph, semi-supervised learning and ranking.

● Knowledge and experience in statistical and data mining techniques: GLM/Regression, Random Forest,
Boosting, Trees, text mining, social network analysis, etc.
● Knowledge on using web services: Redshift, S3, Spark, Digital Ocean, etc.
● Knowledge on creating and using advanced machine learning algorithms and statistics: regression,
simulation, scenario analysis, modeling, clustering, decision trees, neural networks, etc.
● Knowledge on analyzing data from 3rd party providers: Google Analytics, Site Catalyst, Core metrics,
AdWords, Crimson Hexagon, Facebook Insights, etc.
● Knowledge on distributed data/computing tools: Map/Reduce, Hadoop, Hive, Spark, MySQL, Kafka etc.
● Knowledge on visualizing/presenting data for stakeholders using: Quicksight, Periscope, Business Objects,
D3, ggplot, Tableau etc.
● Knowledge of a variety of machine learning techniques (clustering, decision tree learning, artificial neural
networks, etc.) and their real-world advantages/drawbacks.
● Knowledge of advanced statistical techniques and concepts (regression, properties of distributions,
statistical tests, and proper usage, etc.) and experience with applications.
● Experience building data pipelines that prep data for Machine learning and complete feedback loops.
● Knowledge of Machine Learning lifecycle and experience working with data scientists
● Experience with Relational databases and NoSQL databases
● Experience with workflow scheduling / orchestration such as Airflow or Oozie
● Working knowledge of current techniques and approaches in machine learning and statistical or
mathematical models
● Strong Data Engineering & ETL skills to build scalable data pipelines. Exposure to data streaming stack (e.g.
Kafka)
● Relevant experience in fine tuning and optimizing ML (especially Deep Learning) models to bring down
serving latency.
● Exposure to ML model productionzation stack (e.g. MLFlow, Docker)
● Excellent exploratory data analysis skills to slice & dice data at scale using SQL in Redshift/BigQuery.

Responsibilities: 

• Improve robustness of Leena AI current NLP stack 
• Increase zero shot learning capability of Leena AI current NLP stack 
• Opportunity to add/build new NLP architectures based on requirements 
• Manage End to End lifecycle of the data in the system till it achieves more than 90% accuracy 
• Manage a NLP team 

Page BreakRequirements: 

• Strong understanding of linear algebra, optimisation, probability, statistics 
• Experience in the data science methodology from exploratory data analysis, feature engineering, model selection, deployment of the model at scale and model evaluation 
• Experience in deploying NLP architectures in production 
• Understanding of latest NLP architectures like transformers is good to have 
• Experience in adversarial attacks/robustness of DNN is good to have 
• Experience with Python Web Framework (Django), Analytics and Machine Learning frameworks like Tensorflow/Keras/Pytorch. 

1. The candidate should be passionate about machine learning and deep learning.
2. Should understand the importance and know-how of taking the machine-learning-based solution to the consumer.
3. Hands-on experience with statistical, machine-learning tools and techniques
4. Good exposure to Deep learning libraries like Tensorflow, PyTorch.
5. Experience in implementing Deep Learning techniques, Computer Vision and NLP. The candidate should be able to develop the solution from scratch with Github codes exposed.
6. Should be able to read research papers and pick ideas to quickly reproduce research in the most comfortable Deep Learning library.
7. Should be strong in data structures and algorithms. Should be able to do code complexity analysis/optimization for smooth delivery to production.
8. Expert level coding experience in Python.
9. Technologies: Backend - Python (Programming Language)
10. Should have the ability to think long term solutions, modularity, and reusability of the components.
11. Should be able to work in a collaborative way. Should be open to learning from peers as well as constantly bring new ideas to the table.
12. Self-driven missile. Open to peer criticism, feedback and should be able to take it positively. Ready to be held accountable for the responsibilities undertaken.

Benefits: 1)Working with leaders of analytics Guru 2) working under 25+ years of business exp leaders 3) learning to market and sales pitch for product using social media 4) work from home based on your time 5) exp letter from leading analytics firm for 3 months 6) no stiphen