Software Engineer, AI Platforms and Products

The New York Times•New York, NY

7h•$110,000 - $130,000•Hybrid

About The Position

The New AI Products and Platforms mission is a central hub for new, high-ambition AI opportunities and services at The Times. We are hiring a Software Engineer to help build the backend services and infrastructure that will form our internal AI Platform. This platform will enable teams across the company to build, deploy, and manage applications that use large language models (LLMs) to advance our journalism and our business. You will report to the Director of AI Platforms and work with a team of engineers, designers, product and project managers, data scientists, and newsroom stakeholders to make investments in AI possible across The Times.

Requirements

2+ years of software engineering experience, with a focus on backend development.
2+ years of experience in one or more backend programming languages such as Python or Go.
Experience building and operating APIs and services in a production environment.
Exposure to building applications with Large Language Models (LLMs), or familiarity with the surrounding ecosystem (e.g., orchestration, retrieval-augmented generation).

Nice To Haves

Experience with MLOps, including building systems for model and prompt evaluation, tracing, and monitoring
Experience with vector databases and embedding models or services
Experience with information retrieval or search systems
Experience building RAG systems or agentic AI workflows
Experience with prompt engineering and prompt management systems
Familiarity with containerization and orchestration technologies like Docker and Kubernetes
Experience with infrastructure as code (e.g., Terraform, CloudFormation)
Experience with cloud computing platforms like GCP or AWS and their associated services (e.g., Cloud Functions, S3, RDS)
Experience with event-driven architectures and technologies such as Kafka or Pub/Sub
Familiarity with LLM orchestration and agentic frameworks
Experience with GraphQL
Experience designing distributed systems at scale

Responsibilities

Design, build, and maintain scalable and reliable backend services and APIs for a central platform used by teams building AI applications across our journalism and our business
Contribute to and help maintain core platform components and integrations, including systems for prompt and workflow management, evaluation and tracing, and monitoring for cost, usage, and performance
Build and operate vector database and retrieval infrastructure to support search and AI-powered discovery experiences
Design and develop retrieval-augmented generation (RAG) pipelines and agentic workflows that connect our content, data, and AI models
Build orchestration layers for multi-step AI workflows, managing the coordination of LLM calls, retrieval, and business logic
Develop the infrastructure that enables teams to create and manage their AI applications, complete with metadata, observability, and access controls
Implement data pipelines and storage solutions to support our AI systems
Write high-quality, maintainable, and well-tested code, primarily in backend languages like Python or Go
Ensure a high degree of code quality, security, and system observability
Collaborate with editorial, product, ML, and data teams to translate requirements into platform capabilities
Participate in code review, reading teammates' code and providing feedback
Contribute to robust testing strategies to ensure service reliability
Share knowledge with teammates through documentation, design discussions, and pairing
Demonstrate support and understanding of our value of journalistic independence and a strong commitment to our mission to seek the truth and help people understand the world