Amigo builds AI agents for healthcare—systems that handle patient conversations, take clinical actions, and escalate to humans when needed.
Our agents operate autonomously within bounded clinical domains. Clear inclusions, exclusions, and handoff protocols. The scope of autonomous operation expands over time as we validate performance across patient populations.
We own the data foundation end-to-end: patient interactions, agent reasoning traces, outcome data, and synthetic data with known fidelity. This enables population-level analytics and continuous improvement.
Series A from leading investors. Clinical validation and evidence generation in partnership with leading academic medical institutions.
About this roleAs a Senior Software Engineer (Data) at Amigo, you'll build the data infrastructure that powers agent improvement, clinical analytics, and research collaboration. You'll own streaming and batch pipelines on Databricks that process agent conversations, clinical events, and patient outcomes at scale.
Our data platform is a strategic differentiator. We own the entire data foundation—from raw interaction data to agent reasoning traces to clinical outcomes. You'll build pipelines that enable population analysis, data mining, and the Research Platform backend.
What you'll doBuild and maintain streaming and batch pipelines on Databricks (Delta Lake, Spark)
Design CDC pipelines that sync operational databases to Delta Lake for analytics
Implement data mining pipelines for persona discovery, scenario extraction, and edge case detection
Build the data backend for Research Platform, including natural language to SQL capabilities
Create data quality monitoring, staleness detection, and automated alerting
Build pipelines for voice and SMS analytics (call quality, engagement metrics)
Support multi-region data deployment and compliance requirements
Collaborate with agent engineers and data scientists to surface insights that improve agent performance
4+ years of production data engineering experience
Strong experience with Databricks, Spark, and Delta Lake
Proficiency in Python and SQL for pipeline development
Experience building streaming pipelines and CDC (change data capture) systems
Understanding of data modeling, medallion architecture (bronze/silver/gold), and query optimization
Experience with data quality frameworks and monitoring
Track record of building reliable, production-grade data infrastructure
Both execution-oriented and defensive-minded: you ship pipelines while anticipating failure modes
Strong debugging skills for distributed data systems
Clear communication with data scientists, backend engineers, and product teams
Experience with healthcare data or HIPAA compliance requirements
Background with ML pipelines (feature engineering, model training infrastructure)
Experience building natural language query interfaces or LLM-powered data tools
Familiarity with vector search and embedding pipelines
Experience with Delta Sharing or data collaboration protocols
Comprehensive health, dental, and vision insurance
Mental health support and wellness coaching
Flexible wellness stipend for fitness, therapy, or personal growth
Daily catered lunch and dinner
Annual learning budget for courses, books, or conferences
Conference attendance budget for professional development
Development setup of your choice
Academic collaboration opportunities
Top Skills
What We Do
Amigo AI builds trust and safety infrastructure for clinical agents—ensuring AI systems in healthcare provide quantified confidence when mistakes aren't an option. Our platform combines advanced simulation, verification, and recursive optimization to enable healthcare organizations to deploy AI with statistical guarantees about its behavior.
We solve the fundamental challenge of reliable AI in critical domains through deterministic verification for clinical protocols and continuous drift detection for real-world performance. Our systems provide complete transparency—every AI decision is traceable and auditable, with quantified confidence intervals rather than black box predictions.
Founded by technologists from Google, Meta AI, Databricks, Coda, and Plaid, we've built systems that let organizations make informed risk decisions about AI deployment in healthcare. Our interdisciplinary approach draws from computer science, economics, physics, and mathematics to tackle human-centric optimization problems where people and populations are at the center of every solution.
We're actively working with healthcare organizations across digital health, cancer care, cardiac care, and personalized medicine to deploy AI systems that continuously learn and adapt from real-world feedback while maintaining verified safety boundaries. Our technology amplifies human expertise rather than replacing it, empowering domain experts to achieve outcomes neither could accomplish alone.
Why Work With Us
We build AI healthcare systems where 99% isn't good enough. Rapid growth—promotions in 3 months. Freedom to work your way: art museums or late nights. Tackle recursive optimization problems that ship to production. Your work directly impacts critical healthcare decisions. Diverse team from Google, Meta AI, Databricks solving problems that matter.
.png)
