Retail Trade Expert

About the Role

We are looking for a

Data Engineer with strong Generative AI exposure

to design, build, and maintain scalable data pipelines and data platforms that power AI/ML and GenAI applications. The ideal candidate should have strong experience in modern data engineering tools along with hands-on Python development and API frameworks.

Key Responsibilities

• Design, build, and maintain

scalable data pipelines

using modern data engineering tools. • Develop and manage

data transformation workflows

using

dbt and Dagster

. • Build robust

data models and pipelines

supporting analytics and AI workloads. • Develop backend services and APIs using

Python and FastAPI

to enable data access for AI applications. • Work with

PostgreSQL and SQL

to design efficient schemas and optimize queries. • Process and analyze data using

Pandas and Python-based data frameworks

. • Integrate structured and unstructured data pipelines to support

Generative AI applications

. •

Build AI agents using LangGraph

• Implement RAG pipelines and Text-to-SQL systems • Integrate AI capabilities into enterprise platforms • Collaborate with AI/ML engineers to enable

LLM-powered applications and data pipelines

. • Implement

data quality, monitoring, and performance optimization

practices. • Participate in architecture design discussions and contribute to scalable data platform design.

Required Skills

• Strong programming experience in

Python

. • Experience working with

Dagster

for orchestration. • Hands-on experience with

dbt

for data transformation and modeling. • Advanced

SQL

skills and experience with

PostgreSQL

. • Experience working with

Pandas

for data processing. • Experience building APIs using

FastAPI

. • Solid understanding of

data pipeline design and ETL/ELT processes

. • Familiarity with building

data infrastructure for AI/ML or GenAI use cases

.

Good to Have

• Experience designing

Star Schema / Dimensional Data Models

. • Familiarity with

Medallion Architecture (Bronze, Silver, Gold layers)

. • Experience with

Generative AI frameworks or LLM integrations

. • Knowledge of

RAG pipelines, vector databases, or embedding workflows

. • Exposure to cloud platforms such as

AWS / GCP / Azure

.

Vetting Process

• 1 hour technical discussion (Live coding Python) • 30 minutes Technical Discussion • 30 minutes Delivery Connect • In person interview with Customer at NYC, NY