Key Responsibilities
Design and deploy AI agent workflows to automate recurring analytical tasks, data summarization, and insight generation pipelines.
Evaluate and integrate LLM-based tools into the data team’s workflow, assessing their reliability, accuracy, and fitness for analytical use cases.
Collaborate with product and business teams to define analytical questions, success metrics, and KPIs.
Build and maintain analytics foundation using SQL and dbt, enabling reliable reporting and self-serve analytics.
Design, build, and perform weekly maintenance of Tableau dashboards to bring metrics to life, ensuring data accuracy and platform stability for day-to-day decision-making.
Perform A/B testing and experimentation, including experiment design, statistical inference, significance testing, and result interpretation.
Perform ad-hoc, exploratory, and statistical analyses to uncover insights and validate hypotheses.
Communicate findings clearly to both technical and non-technical stakeholders, translating data into actionable recommendations.
Partner with stakeholders to design, develop, and iterate on key metrics, interactive dashboards, and data analyses to support evolving business needs.
Qualifications
5+ Years of experience in Similar roles
Hands-on experience with AI agent frameworks (e.g., LangChain, LlamaIndex, CrewAI, or similar) and demonstrated ability to build and deploy agentic systems in a production or near-production context.
Proven experience with prompt engineering and evaluating LLM outputs for data-related tasks such as automated reporting, anomaly narration, or natural language querying.
Experience orchestrating multi-step AI pipelines that combine LLMs with structured data sources, APIs, or internal tooling.
Strong SQL and Python skills for data analysis and modeling.
Experience with dbt for analytics engineering workflows.
Experience building dashboards in Tableau
Solid foundation in statistics, experimentation, and hypothesis testing.
Ability to work cross-functionally and communicate insights effectively.
Nice to Have
Exposure to cloud platforms (AWS) for data storage or analytics workloads.
Knowledge of feature engineering and model evaluation concepts.
Experience with version control (Git).
Compensation
Additional Information