Build AI systems: Design, develop and maintain production AI solutions, including LLM-based applications, retrieval-augmented generation (RAG) pipelines, agentic workflows and ML model services.
Productionize models: Take models and prototypes from applied scientists and turn them into robust, low-latency, cost-efficient services that scale to global traffic.
Evaluation and quality: Define and automate evaluation frameworks, benchmarks and guardrails that measure accuracy, safety, latency and cost, and monitor models once they're in production.
Data and pipelines: Build and optimize data pipelines for training, fine-tuning, embedding and inference, making sure data is high quality, traceable and handled in line with privacy requirements.
MLOps and infrastructure: Implement CI/CD for ML, model versioning, experiment tracking and observability on cloud platforms.
Cross-functional collaboration: Work with product, engineering and science stakeholders to understand requirements, weigh trade-offs and deliver AI solutions that meet customer needs.
Continuous improvement: Keep up with the fast-moving AI ecosystem, evaluate new models, tools and techniques, and share what you learn with the wider engineering community.
Strong proficiency in one or more high-level programming languages such as C++, Java, Python, or similar languages.
Hands-on experience with LLMs and their ecosystem: prompt engineering, RAG, embeddings and vector databases, tool use and agent frameworks, and fine-tuning is preferred.
Solid understanding of software architecture, API design, design patterns and best practices for maintainable, scalable systems.
Experience with cloud service providers (e.g., Azure, AWS, GCP), containerization (Docker, Kubernetes) and CI/CD tools.
Knowledge of version control systems, preferably Git.
Excellent problem-solving and communication skills, with the ability to work effectively in a cross-functional team.
Experience with ML frameworks and libraries such as PyTorch, TensorFlow or Hugging Face is preferred.
Familiarity with MLOps practices and tools (e.g., MLflow, experiment tracking, model monitoring) is preferred.
Experience with geospatial, mapping or location data is a plus, but not required.
Identify high-impact business workflows, redesign them for AI agents, connect systems, and deploy and operate production agents while tracking quality, efficiency, cost, and business outcomes.
Own AI-powered healthcare product features end to end, from defining ambiguous problems with clinicians and operators to building, deploying, and monitoring full-stack workflows in production.
Design, build, and ship production-ready AI-powered web products end to end, combining full-stack engineering, intuitive interfaces, production LLM features, and reliable infrastructure.
Build production services, internal tools, and customer integrations for AI agents, developing reliable primitives and workflows for tasks such as meetings, browsing, search, email, and payments.
Deploy ProcessOS into enterprise production, owning customer workflows from initial process files through measurable improvement, while building product features, custom agents, and repeatable deployment practices.
