AI Engineering Intern

About Time Seventeen

Time Seventeen builds infrastructure for geopolitical risk and catastrophe risk by creating tradable synthetic indices and term structures for tail events. Our ambition is to transform fragmented judgments about individual events into continuous risk prices, integrating them into institutional valuation, trading, and risk-transfer workflows. Our work connects event definitions, probabilistic forecasting, market data, index methodology, and execution infrastructure. We explore how prediction markets, actuarial models, insurance and reinsurance structures, and blockchain-based DeFi can contribute to a common language for uncertain outcomes. The challenge is to make risk legible across different horizons, exposures, and market participants, while keeping assumptions and limitations explicit. Building this infrastructure requires traceable data, defensible event resolution rules, robust methodologies, and products that account for liquidity, basis risk, operational resilience, and applicable legal constraints.

About the Role

Build and evaluate AI workflows that transform research ideas into practical tools for event analysis and risk infrastructure. You will work on the engineering path from an AI prototype to a dependable workflow, encompassing document ingestion, retrieval, structured extraction, tool integration, and interfaces that expose the evidence behind an output. You will learn to make behavior measurable and failures visible, collaborating with research and product colleagues on a bounded project with clear user and acceptance criteria. The work will involve iteration across functionality, latency, cost, reliability, and output quality, with careful attention to how the system behaves when sources or models change.

Key Responsibilities

• Build small services and workflows around model APIs, retrieval systems, and structured event data.
• Implement input validation, output schemas, retries, error handling, and useful logging.
• Create evaluation cases for factual support, extraction accuracy, and workflow completion.
• Measure latency and cost and investigate bottlenecks without obscuring quality tradeoffs.
• Connect prototypes to usable APIs or interfaces and document their dependencies.
• Review code with engineering colleagues and help turn validated experiments into reusable components.

Requirements & Tech Stack

• Practical Python or TypeScript experience and an ability to build and debug a working application.
• Familiarity with APIs, databases, version control, and basic software testing.
• Experience experimenting with language models, retrieval, or other AI tooling.
• An interest in reliable systems and evidence-based evaluation.
• A project or code sample that demonstrates your contribution and ability to learn.

Qualifications

Successful candidates will be able to:

• Ship a working AI workflow with clear inputs, outputs, and failure handling.
• Make quality, latency, and cost inspectable through evaluation and instrumentation.
• Leave code and documentation that colleagues can run and extend.

This role is associated with San Francisco and supports remote work.

Please share your location, time zone, availability, and ability to coordinate with colleagues in San Francisco and Hong Kong.