Analytics engineer in the Analytics Engineering team at 2degrees, working daily in dbt, Snowflake and SQL. I turn complex, fragmented source data into clean, tested, well-governed models that both reporting and AI systems can rely on, and I have spent the last two years retiring legacy reporting platforms and rebuilding what was inside them.
I came up through BI and reporting, then got more interested in the layer underneath the dashboards: how data gets modelled, tested and governed before anyone sees a chart. That is the work I do now. Much of the last two years has gone into retiring legacy platforms, SAP BusinessObjects and Netezza, and rebuilding the business logic buried inside them as governed Snowflake models, so teams query a model instead of raising a request for a report.
A lot of what I build sits on sensitive and regulated data, so access control, lineage and auditability are part of building the model rather than something added at the end.
I also helped build the retrieval-augmented generation (RAG) pipeline for KiwiStart, an AI product for migrants and students. That gave me hands-on experience with the part of AI most analytics people never touch: the data and retrieval layer that decides whether the answers are any good.
Selected work
Real work at 2degrees and beyond. Where a dataset is sensitive, the detail is withheld and only the transferable skill is shown.
Worked with data leadership and report owners to take more than 100 reports off SAP BusinessObjects, rebuild the business logic inside them as governed Snowflake models, and move users onto Power BI or direct SQL. Saved over NZ$150,000 a year.
Reassembled fragmented source records into complete, auditable activity for a high-sensitivity regulatory dataset, using window functions and layered CASE logic on incremental, micro-batched tables.
End-to-end dbt pipeline bringing ServiceNow incidents, cases and SLA data into the warehouse for SLA and resolution reporting, with data contracts enforced across layers.
Helped build the retrieval-augmented generation pipeline behind KiwiStart's AI chat: the knowledge base, embeddings and vector search that decide what the model retrieves before it answers.
Took over Tableau licence management for the wider business, reviewed what each team genuinely needed instead of handing out authoring licences by default, and reduced the estate from around 200 licences to 5 as reporting consolidated onto Power BI.
Helped move reporting and data workloads off the decommissioned Netezza platform onto Snowflake: analysing existing solutions, rebuilding transformation logic, validating outputs, and keeping things steady for business users.
The skills map
Where this is heading
The semantic and governance layer is becoming the thing AI reads. The plan is to own it as an analytics engineer, then build AI engineering on top of the same foundation.
dbt + Snowflake mastery, semantic layer, governance and orchestration, backed by dbt and SnowPro certifications and a public portfolio.
Python, RAG and agents, LLM-on-data, one GenAI credential, built on top of the data foundation, not instead of it.
Get in touch
kishoremohini13@gmail.com
linkedin.com/in/kishoremohini-1109
Auckland, New Zealand · open to Australia