ML Engineer

FanCode is India’s premier sports destination committed to giving fans a highly personalised experience across content and merchandise for a wide variety of sports. Founded by sports industry veterans Yannick Colaco and Prasana Krishnan in March 2019, FanCode has over 100 million users. It has partnered with domestic, international sports leagues and associations across multiple sports. In content, FanCode offers interactive live streaming for sports with industry-first subscription formats like Match, Bundle and Tour Passes, along with monthly and annual subscriptions at affordable prices. Through FanCode Shop, it also offers fans a wide range of sports merchandise for sporting teams, brands and leagues across the world.
Data Science @FanCodeWe have one mission, Create a platform for all sports fans. Built by  sports fans for sports fans. We’re at the beginning of our story and growing at an incredible pace. 
At FanCode we are crafting a one-of-a-kind personalized experience for avid sports fans. Our guiding principle is to enhance and automate decision-making capabilities for the organisation by identifying and utilizing complex patterns in underlying data. We are developing state-of-the-art data-driven solutions to refine user experience and build innovative data products. Your Role:

• Communicate with the Product and Management teams to understand business requirements and user problems
• Carry out EDA in collaboration with the Analytics team to identify solutions and research industry best practices and tools for its implementation
• Build data ingestion pipelines, models and serving layers, and deploy them by working closely with the Tech team
• Communicate the solutions’ business impact, caveats and implementation deadlines to all stakeholders
• Broadly 60%-70% of time dedicated to Model Deployment work-streams and rest to Model Development

Must Haves:

• 3-5 years experience in developing, delivering and maintaining data-driven solutions  (Ex: recommendation systems, traffic forecasting, dynamic pricing, video and text processing)
• Good understanding of fundamental statistics and ML concepts (Ex: hypothesis testing, linear and ensemble models, graph analytics, deep learning)
• Expert-level grasp on Python programming language and SQL (Ex: OOPs, async-await paradigm, CTEs, window functions)
• Hands-on experience with creating data ingestion pipelines and APIs that serve model results at scale (Ex: Spark, FastAPI, Celery)
• Ability to break down business requirements into technical problems and communicate solutions to other teams

Good to Haves:

• Bachelor's degree in a quantitative discipline - Engineering, Statistics, Mathematics, Economics etc.
• Ability to identify and integrate innovative tools which can help build more efficient solutions
• Love for sports
• Experience building NLP and computer vision applications
• Data visualization skills