Surgo Health

AI-powered socio-behavioral analytics for healthcare

Data Engineer

Data EngineeringUpdated on Nov 13

Full-timeİstanbul, TürkiyeNo salary listed

About the Job

Requirements

At least 3 years of experience in data engineering, building production pipelines in Python and SQL.
Hands-on production experience with Databricks, including Spark, Delta Lake, Unity Catalog, and Lakeflow or Jobs.
Strong relational database skills, particularly PostgreSQL, including schema design, query optimization, replication, or change data capture.
Hands-on experience with Microsoft Azure, infrastructure as code, and continuous integration and continuous delivery.
Experience modeling data for analytics and business intelligence using dimensional or long/wide formats, with attention to data quality and testing.
Use agentic tools such as Claude Code and Cursor daily to design architectures and diagrams, write and review code, debug, and improve performance; know how to configure context, rules, MCP servers, and subagents, and when not to trust their output.
A university degree in Computer Science or a related field.
Fluency in written and spoken English and comfort working remotely with substantial overlap with US Eastern and UK hours.

Responsibilities

Own the Databricks data platform behind Derin, from ingesting interview and survey data to delivering analytics-ready tables used by the product, scientists, and clients.
Design and build reliable batch and incremental pipelines on Databricks using Lakeflow Spark Declarative Pipelines, Jobs, and Delta Lake, and govern them in Unity Catalog.
Help move the production data layer to Databricks Lakebase, including synced tables, migration, and cutover, and keep the serving layer fast for APIs.
Model survey and conversation data in Delta Lake so it is easy to access for downstream analytics products.
Make pipelines observable and trustworthy through data-quality checks such as Lakeflow expectations, tests, Unity Catalog lineage, monitoring, and alerting.
Turn scientists' Databricks notebooks and analyses into production-grade, reusable pipelines.
Build privacy and security into handling sensitive participant data using Unity Catalog access controls, row filters, and column masks in a SOC2- and HIPAA-compliant environment.
Use Terraform, Databricks Asset Bundles, and CI/CD to deploy data workloads across environments.
Contribute to shaping the engineering culture and data platform as the organization grows.
Use AI agents such as Claude Code and Cursor throughout the day to design, build, debug, and optimize, and help the team improve AI-assisted engineering.

Desired Qualifications

Experience serving data to LLM-powered features such as text-to-SQL, RAG, Databricks metric views, Genie, or other semantic layers.
Experience with survey, research, healthcare, or regulated data such as HIPAA or GDPR/KVKK.

Surgo Health is building the Behavioral Intelligence layer for healthcare — revealing why people behave as they do, predicting what they will do next, and helping organizations make the decisions that change outcomes.

A Public Benefit Corporation grounded in two decades of global health experience, Surgo generates foundational behavioral data that reveals the unseen why and builds the AI products that power decision-grade insights at population scale — equipping healthcare organizations, funders, and public agencies to act on what actually shapes health outcomes: people's beliefs, motivations, and barriers.

Backed by 40+ peer-reviewed publications and trusted by partners including the Gates Foundation, J&J, Takeda, Pivotal Ventures, and the Clinton Health Access Initiative, Surgo is building a future where healthcare organizations don't just understand human behavior, but anticipate it.

Role Summary:

We are looking for a Data Engineer to join the R&D Engineering team building Derin, our AI-powered interview platform. Derin runs conversational, LLM-led interviews over WhatsApp/SMS, web and voice, and turns thousands of conversations into structured data that our scientists and clients use to ultimately improve patients’ outcomes.

You will own the data layer behind all of this: the pipelines that move interview data from our application into our Databricks lakehouse, the models that make it analysis-ready, and the serving layer (Postgres/Lakebase) that our product reads from in real time. You will work side by side with backend engineers, data scientists and product managers, in a small team where your work reaches clients quickly.

Work AI-first: use AI agents (Claude Code, Cursor and others) throughout your day to design, build, debug and optimize, and help the team keep raising the bar on AI-assisted engineering
Own the Databricks data platform behind Derin, from ingestion of interview and survey data to the analytics-ready tables our product, scientists and clients rely on
Design and build reliable batch and incremental pipelines on Databricks (Lakeflow Spark Declarative Pipelines, formerly Delta Live Tables; Jobs; Delta Lake) and govern them in Unity Catalog
Help move our production data layer to Databricks Lakebase (managed Postgres), including synced tables, migration and cutover, and keep the serving layer fast for our APIs
Model survey and conversation data in Delta Lake so it is easy to access for downstream analytics products
Make pipelines observable and trustworthy: data-quality checks (such as Lakeflow expectations), tests, Unity Catalog lineage, monitoring and alerting
Turn scientists' Databricks notebooks and analyses into production-grade, reusable pipelines
Build privacy and security into how we handle sensitive participant data, using Unity Catalog access controls, row filters and column masks, in a SOC2 and HIPAA-compliant environment
Use infrastructure as code (Terraform, Databricks Asset Bundles) and CI/CD to deploy data workloads across environments
Contribute to shaping our engineering culture and data platform as we grow

You have at least 3 years of experience in data engineering, building production pipelines in Python and SQL
You have hands-on production experience with Databricks (Spark, Delta Lake, Unity Catalog, Lakeflow or Jobs)
You are strong with relational databases, particularly PostgreSQL (including Databricks Lakebase): schema design, query optimization, replication or CDC
You have hands-on experience with Microsoft Azure (required) and with infrastructure as code and CI/CD
You have modelled data for analytics and BI (dimensional or long/wide formats) and care about data quality and testing
Experience serving data to LLM-powered features (text-to-SQL, RAG, Databricks metric views, Genie or other semantic layers) is a strong plus
Experience with survey, research or healthcare data, or with regulated data (HIPAA, GDPR/KVKK), is a plus
You are AI-native: you use agentic tools such as Claude Code and Cursor every day to design architectures and diagrams, write and review code, debug and improve performance. You know how to set them up (context, rules, MCP servers, subagents) and when not to trust their output. Surgo is an AI-driven company that uses AI for almost everything we do, not only code, and our interview process asks you to show how you work with it
You hold a University degree in Computer Science or a related field
You are independent, proactive, and able to deliver end-to-end with minimal supervision
You are fluent in English, both written and spoken, and comfortable working remotely with substantial overlap with US Eastern and UK hours

Location: This is a Türkiye-based role (Istanbul only). Surgo is headquartered in Washington, DC, with team members across the US, UK, Türkiye, Brazil and India.

About the Company

Surgo Health

AI-powered socio-behavioral analytics for healthcare

Surgo Health runs an AI-powered socio-behavioral analytics platform that helps healthcare organizations understand why people engage with care, using a cloud-based SaaS model for pharma, payers, and providers. Its Mosaic platform maps drivers of health behavior by combining behavioral, clinical, and social data; MosaicTrials improves clinical trial design, recruitment, and diversity; and Derin uses conversational AI to collect health-behavior insights at scale. It differentiates itself by explaining the underlying beliefs, biases, and trust behind patient actions beyond standard clinical data and SDOH, and operates as a public benefit corporation focused on equity. The company aims to advance health equity and improve health outcomes through data-driven, behaviorally informed insights.

Company size: 51-200
Company stage: Seed
Total funding: $5M
Headquarters: Washington DC, United States
Founded: 2022

Recently Posted Jobs

Explore more opportunities at Surgo Health

See more jobs