Data Scientist

At Livello we building machine-learning-based demand forecasting tools as well as computer-vision-based multi-camera product recognition solutions that detects people and products to track the inserted/removed items on shelves based on the hand movement of users. We are building models to determine real-time inventory levels, user behaviour as well as predicting how much of each product needs to be reordered so that the right products are delivered to the right locations at the right time, to fulfil customer demand.

Responsibilities

• Lead the CV and DS Team
• Work in the area of Computer Vision and Machine Learning, with focus on product (primarily food) and people recognition (position, movement, age, gender, DSGVO compliant).
• Your work will include formulation and development of a Machine Learning models to solve the underlying problem.
• You help build our smart supply chain system, keep up to date with the latest algorithmic improvements in forecasting and predictive areas, challenge the status quo
• Statistical data modelling and machine learning research.
• Conceptualize, implement and evaluate algorithmic solutions for supply forecasting, inventory optimization, predicting sales, and automating business processes
• Conduct applied research to model complex dependencies, statistical inference and predictive modelling
• Technological conception, design and implementation of new features
• Quality assurance of the software through planning, creation and execution of tests
• Work with a cross-functional team to define, build, test, and deploy applications

Requirements:

• Master/PHD in Mathematics, Statistics, Engineering, Econometrics, Computer Science or any related fields.
• 3-4 years of experience with computer vision and data science.
• Relevant Data Science experience, deep technical background in applied data science (machine learning algorithms, statistical analysis, predictive modelling, forecasting, Bayesian methods, optimization techniques).
• Experience building production-quality and well-engineered Computer Vision and Data Science products.
• Experience in image processing, algorithms and neural networks.
• Knowledge of the tools, libraries and cloud services for Data Science. Ideally Google Cloud Platform
• Solid Python engineering skills and experience with Python, Tensorflow, Docker
• Cooperative and independent work, analytical mindset, and willingness to take responsibility
• Fluency in English, both written and spoken.

Introduction

http://www.synapsica.com/">Synapsica is a https://yourstory.com/2021/06/funding-alert-synapsica-healthcare-ivycap-ventures-endiya-partners/">series-A funded HealthTech startup founded by alumni from IIT Kharagpur, AIIMS New Delhi, and IIM Ahmedabad. We believe healthcare needs to be transparent and objective while being affordable. Every patient has the right to know exactly what is happening in their bodies and they don't have to rely on cryptic 2 liners given to them as a diagnosis. 

Towards this aim, we are building an artificial intelligence enabled cloud based platform to analyse medical images and create v2.0 of advanced radiology reporting.  We are backed by IvyCap, Endia Partners, YCombinator and other investors from India, US, and Japan. We are proud to have GE and The Spinal Kinetics as our partners. Here’s a small sample of what we’re building: https://www.youtube.com/watch?v=FR6a94Tqqls">https://www.youtube.com/watch?v=FR6a94Tqqls 

Your Roles and Responsibilities

We are looking for an experienced MLOps Engineer to join our engineering team and help us create dynamic software applications for our clients. In this role, you will be a key member of a team in decision making, implementations, development and advancement of ML operations of the core AI platform.

• Work closely with a cross functional team to serve business goals and objectives.
• Develop, Implement and Manage MLOps in cloud infrastructure for data preparation,deployment, monitoring and retraining models
• Design and build application containerisation and orchestrate with Docker and Kubernetes in AWS platform. 
• Build and maintain code, tools, packages in cloud

• At Least 2+ years of experience in Data engineering 
• At Least 3+ yr experience in Python with familiarity in popular ML libraries.
• At Least 2+ years experience in model serving and pipelines
• Working knowledge of containers like kubernetes , dockers, in AWS
• Design distributed systems deployment at scale
• Hands-on experience in coding and scripting
• Ability to write effective scalable and modular code.
• Familiarity with Git workflows, CI CD and NoSQL Mongodb
• Familiarity with Airflow, DVC and MLflow is a plus

- Modeling complex problems, discovering insights, and identifying opportunities through the use of statistical, algorithmic, mining, and visualization techniques

- Experience working with business understanding the requirement, creating the problem statement, and building scalable and dependable Analytical solutions

- Must have hands-on and strong experience in Python

- Broad knowledge of fundamentals and state-of-the-art in NLP and machine learning

- Strong analytical & algorithm development skills

- Deep knowledge of techniques such as Linear Regression, gradient descent, Logistic Regression, Forecasting, Cluster analysis, Decision trees, Linear Optimization, Text Mining, etc

- Ability to collaborate across teams and strong interpersonal skills

Skills

- Sound theoretical knowledge in ML algorithm and their application

- Hands-on experience in statistical modeling tools such as R, Python, and SQL

- Hands-on experience in Machine learning/data science

- Strong knowledge of statistics

- Experience in advanced analytics / Statistical techniques – Regression, Decision trees, Ensemble machine learning algorithms, etc

- Experience in Natural Language Processing & Deep Learning techniques 

- Pandas, NLTK, Scikit-learn, SpaCy, Tensorflow

Required skill

• Around 6- 8.5 years of experience and around 4+ years in AI / Machine learning space
• Extensive experience in designing large scale machine learning solution for the ML use case,  large scale deployments and establishing continues automated improvement / retraining framework.
• Strong experience in Python and Java is required.
• Hands on experience on Scikit-learn, Pandas, NLTK
• Experience in Handling of Timeseries data and associated techniques like Prophet, LSTM
• Experience in Regression, Clustering, classification algorithms
• Extensive experience in buildings traditional Machine Learning SVM, XGBoost, Decision tree and Deep Neural Network models like RNN, Feedforward is required.
• Experience in AutoML like TPOT or other
• Must have strong hands on experience in Deep learning frameworks like Keras, TensorFlow or PyTorch 
• Knowledge of Capsule Network or reinforcement learning, SageMaker is a desirable skill
• Understanding of Financial domain is desirable skill

 Responsibilities 

• Design and implementation of solutions for ML Use cases
• Productionize System and Maintain those
• Lead and implement data acquisition process for ML work
• Learn new methods and model quickly and utilize those in solving use cases