Job description:
### **About Us**
**Delty is building the healthcare’s AI operating system**. We create voice-based and computer-based assistants that streamline clinical workflows, reduce administrative burden, and help providers focus on patient care. Our system learns from real healthcare environments to deliver reliable, context-aware support that improves efficiency and elevates the provider experience.
Delty was founded by former engineering leaders from **Google, including co-founders with deep experience at YouTube and in large-scale infrastructure**. You’ll get to work alongside people who built massive systems at scale — a chance to learn a _lot_ and contribute meaningfully from day one.
We believe in solving hard problems together as a team, iterating quickly, and building software with long-term thinking and ownership.
* * *
### What You’ll Do
* **Build and own production machine learning systems end-to-end**: from data modeling and feature engineering to training, evaluation, deployment, and monitoring.
* **Design and implement data pipelines** that turn raw, messy real-world healthcare data into reliable features for machine learning models.
* **Train and evaluate models** for ranking, prioritization, and prediction problems (for example, identifying high-risk or high-priority cases).
* **Deploy models into production** as reliable services or batch jobs, with clear versioning, monitoring, and rollback strategies.
* **Work closely with backend engineers and product leaders** to integrate machine learning into real workflows and decision-making systems.
* **Make architectural decisions** around model choice, evaluation metrics, retraining cadence, and system guardrails — balancing accuracy, explainability, reliability, and operational constraints.
* **Collaborate directly with founders and engineers** to translate product and operational needs into scalable, maintainable machine learning solutions.
* * *
### What We’re Looking For
* **At least 3 years of experience** building and deploying machine learning systems in production.
* **Strong foundation in machine learning** for structured (tabular) data, including feature engineering, regression or classification models, and ranking or prioritization problems.
* **Experience with the full machine learning lifecycle**: data preparation, train/test splitting, evaluation, deployment, retraining, and monitoring.
* **Solid backend engineering skills**: writing production-quality code, building services or batch jobs, and working with databases and data pipelines.
* **Good system design instincts**: you understand trade-offs between model complexity, reliability, latency, scalability, and maintainability.
* **Comfort working in a fast-paced startup environment with high ownership and ambiguity**.
* **Ability to clearly explain modeling choices,** assumptions, and limitations to non-machine-learning stakeholders.
**Bonus:**
* Experience working with healthcare or operational decision-support systems.
* **Experience building or integrating LLM systems** in production, such as retrieval-augmented generation, fine-tuning, or structured prompting workflows.
* **Prior startup experience or founder mindset** — we value ownership, pragmatism, and bias toward shipping.
* Experience with model monitoring, data drift detection, or **ML infrastructure tooling**.
* * *
### Why join
* **Learn from seasoned Google engineers**: As former Google engineers who built systems at YouTube and Google Pay, we’ve operated at massive scale. Working alongside us gives you a chance to build similar systems and learn best practices, scale thinking, and software design deeply.
* **High impact**: At a small but ambitious team, your contributions will influence architecture, product direction, and core features. You will have real ownership and see the effects of your work quickly.
* **Grow fast**: We’re iterating rapidly; you’ll be exposed to the full stack, AI/ML pipelines, system architecture, data modeling, and product-level decisions — a fast-track to becoming a senior engineer or technical lead.
* **Challenging and meaningful work**: We’re tackling the hardest part of software engineering: bridging AI-generated prototypes and robust, scalable enterprise-grade systems. If you enjoy thinking deeply about systems and building reliable, maintainable foundations — this is for you.