Job description
About the position
As the Lead Data Scientist for the AI Labs team, you will serve as the technical and ethical anchor for NPR's artificial intelligence initiatives. You will lead data science expertise for a content metadata overhaul to power new audience-focused personalization engines. Rather than building models from scratch, you will focus on fine-tuning, evaluating, and scaling existing foundational models, as well as deploying machine learning algorithms for public media. You will collaborate extensively across the organization to align architectures, ensure secure cloud deployments, and protect intellectual property. This position demands a high focus on accuracy, journalistic ethics, data privacy, and responsible scaling.
Responsibilities
Lead the selection, fine-tuning, and optimization of open-source and proprietary LLMs tailored to NPR’s unique content voice.Design and architect automated machine learning pipelines to transform decades of unstructured audio, transcripts, and text to support automated semantic metadata generation.Collaborate with the product, design and engineering teammates to translate user needs into production-ready data science workflows.Architect recommendation frameworks that leverage enriched metadata to drive deep, style-based audience personalization while preserving editorial curation.Partner with Data Products to construct clean, self-service data pipelines and audience analytics models inside BigQuery.Support newsroom research through the prototyping, validation, and development of API-driven tooling and secure database search models.Establish strict evaluation, testing, and benchmarking frameworks to guarantee model outputs meet NPR’s standards for factual accuracy and neutrality.Proactively identify, audit, and mitigate algorithmic bias in metadata generation and audience discovery systems.Ensure all AI applications scale securely and cost-effectively, balancing computational efficiency with rigorous data privacy guardrails.Collaborate with growth and data platforms to leverage content metadata for user lifecycle retention and smart audience segmentation.Requirements
8+ years of professional experience in Data Science, Machine Learning, or Natural Language Processing (NLP) shipping production-grade systems.Proven track record of applying, fine-tuning, and evaluating Large Language Models (LLMs) and foundational architectures.Experience with Automatic Speech Recognition (ASR), diarization, and audio preprocessing pipelines.Demonstrated experience designing and maintaining large-scale data architectures, vector databases, and semantic search pipelines.Hands-on experience designing, deploying, and optimizing production-grade recommendation engines or personalization systems at scale.Practical, hands-on experience building machine learning workflows within major cloud environments (Azure, AWS or GCP).Experience successfully navigating matrixed, cross-disciplinary collaboration between technical engineering teams and non-technical stakeholders.Ability to identify common AI pitfalls, such as hallucinations or formatting errors, and design robust algorithmic workarounds.Deep technical expertise in Python, ML and agentic engineering frameworks, vector search engines and two-stage retrieval architectures.Strong proficiency in SQL and cloud data warehouse ecosystems (such as BigQuery or Snowflake).Deep understanding of Retrieval-Augmented Generation (RAG) patterns and semantic search tools.Professional-level familiarity with model evaluation methodologies, prompt engineering techniques, and API integration workflows.Strong commitment to algorithmic ethics, data privacy compliance, and methods for identifying or mitigating bias.Nice-to-haves
Experience working with large volumes of unstructured multimedia, digital audio processing, or automated speech-to-text workflows.Prior experience working within a media organization, digital newsroom, or public service institution.Experience integrating automated LLM evaluation gates and regression testing directly into CI/CD deployment pipelinesBenefits
Access to health and wellnessPaid time offFinancial well-beingMedical insuranceDental insuranceVision insuranceLife/ accidental death and dismemberment insuranceLong-term disability insuranceShort-term disability insuranceVoluntary retirement savings
Prepare your application
Use the description above to assess your fit for NPR. This checklist is guidance from Resumize, rather than additional requirements from the employer. Imported listings can be shortened or change after collection, so confirm the complete description and current availability before sending an application.
Match requirements to evidence
Identify the responsibilities and skills the employer explicitly names. For each important requirement, choose one example from your work, education, training, or projects. Explain what you did, how you did it, and what changed as a result. Include a measurable outcome when you can support it. If you lack a requirement, describe related experience accurately instead of adding an unfamiliar skill to your resume.
Put the most relevant examples near the top of your resume. Keep job titles, dates, qualifications, and contact details consistent across your application materials. Use the employer’s terminology when it describes your experience accurately; a copied list of keywords does not explain your contribution. A short, specific bullet is easier to review than a paragraph that mixes several unrelated duties.
Check the working arrangement
Confirm the location, schedule, employment type, and any eligibility requirements on the employer’s site. A remote label does not establish worldwide eligibility or flexible hours. If compensation, benefits, equipment, travel, or contract duration are missing from this listing, write down your questions for the recruiter. Do not assume details from another opening at the same company apply to this role.
Review before submitting
Follow the employer’s requested file format and application instructions. Open your exported resume and check that its text is selectable, its sections read in order, and its links work. Proofread names, dates, and contact information. Share confidential work samples only when you have permission, and use an anonymized example when necessary.
Submit through a trusted employer or recruiting destination. If the original listing has disappeared, search the employer’s careers page for the title rather than assuming the vacancy remains open. Save the application date, job reference, and the version of your resume you sent. Those details help you prepare for a later conversation and avoid submitting conflicting information through several job boards.
Review your resume for writing and readability feedback, or browse other openings if this opportunity is unavailable.