Data Scientist
About Youth Impact
Youth Impact’s mission is to connect youth to proven life-changing information. Our vision is to enable over 1 million youth to thrive through delivery of multiple evidence-based programs. We are at an inflection point in our growth: we have over 350 staff, three programs in health and education, have delivered over two million lessons to over 300,000 youth across 20+ countries. Our culture is unique: we are always learning, have a dynamic team, a fierce commitment to measurement and evidence, and work hand in hand with governments. On any given day our leaders will sing and dance, negotiate MOUs, and spend dedicated time with the field team in schools.
Background
The Government of Karnataka, India, has launched a dedicated program Ganitha Ganaka to improve foundational numeracy in the state. The initiative is grounded in evidence (based on a program called ConnectEd) which is implemented and has been tested in randomized controlled trials by Youth Impact in multiple countries. It is an innovative one-on-one phone-based tutoring initiative for students in grades 3, 4, and 5 and it has demonstrated significant improvements in learning outcomes in diverse contexts. Ganitha Ganaka leverages skills and capacity of government school teachers to deliver tutoring using principles such as targeted instruction, similar to principles embedded in Teaching at the Right Level programs. The program is now expanding to 93 blocks, with over 35,000 teachers set to tutor around 100,000 students weekly, aiming to achieve transformative results in numeracy skills across Karnataka.
Roles & Responsibilities
Ensure seamless collection and flow of large-scale data from multiple channels (e.g. IVR, chatbots, or apps)
Build and manage efficient and secure databases to handle program data, ensuring scalability for interventions like ‘ConnectEd’
Develop automated workflows to clean, process, and normalize raw data for reliable reporting and analysis
With guidance, help develop interactive dashboards (e.g. Tableau, Power BI) to visualize key indicators e.g. teacher participation, learning outcome trends, and other actionable insights
Mentor and teach technical research team members how to maintain dashboards and follow data management protocols
Work closely with program teams, software engineers, and researchers to ensure data accuracy, alignment with program goals, and support evaluation frameworks
Skills & Experience
Multiple years of experience in designing and maintaining enterprise data models .
Ability to integrate and process data from multiple sources applying ETL processes
Experience with data cleaning and processing pipelines using Python or R
Experience with cloud data warehousing solutions (e.g. BigQuery, Redshift, Snowflake or similar)
Write and optimize complex SQL queries to manage and extract insights from large-scale program data, ensuring efficient data retrieval and analysis
Develop and implement predictive models to forecast student learning outcomes, teacher engagement, and program impact using machine learning techniques
Expertise in creating dashboards using. Tableau, Power BI, or similar tools as well as enhancing these real-time, interactive dashboards to provide key stakeholders with actionable insights, improving decision-making and program implementation
With Program teams, design and analyze A/B tests to optimize program cost-effectiveness and scalability
Ability to document workflows and train non-technical team members to use dashboards and tools effectively
Required characteristics
Attitude: Dedicated and hard-working with excellent ownership and accountability
Energy & motivation: Enthusiastic, youthful, energetic, innovative, goal-oriented self-starter, willing to go the extra mile
Analytical skills: Analytical & problem-solving abilities
Organizational skills: Ability to prioritize projects & manage time & resources effectively. Using logic & good judgment
Reporting structure
The candidate will work closely with the Head of Partnerships, India, and will have a technical dotted line to the Head of Research.
Deadline
Deadline: 7 May 2025, 23:59 CAT
Location
Location: Bangalore, India