Applied AI Evaluation Scientist

🕒 February 25

🇺🇸 United States – Remote

💵 $180k - $270k / year

⏰ Full Time

🟡 Mid-level

🟠 Senior

🤖 Artificial Intelligence

Apply Now
Find Similar Remote Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Logo of Jump - Advisor AI

Jump - Advisor AI

51 - 200 employees

Founded 2023

🤖 Artificial Intelligence

💳 Fintech

☁️ SaaS

💰 $24.6M Series A - Jump on 2025-02

Artificial Intelligence • Fintech • SaaS

Jump - Advisor AI is an AI-powered SaaS platform that automates administrative and client-facing workflows for financial advisors and wealth teams. It provides meeting preparation, automated note-taking, follow-up email generation, client engagement tools, and data-driven insights, while integrating with CRMs, financial planning tools, conferencing systems, and calendars. Built with enterprise-grade security and configurable compliance controls, Jump is designed for RIAs, broker-dealers, and other advisory firms to save time, increase meeting capacity, and simplify supervision and auditability.

📋 Description

• Design and curate evaluation datasets for retrieval quality • Measure retrieval quality using metrics like Recall@k, Precision@k, MRR, and NDCG@k • Recommend data cleaning/normalization strategies • Evaluate and optimize chunking strategies • Assess embedding and re-ranking strategies • Evaluate generation quality in context • Attribute failures across the pipeline • Conduct systematic error analysis on AI/ML system outputs • Design and validate LLM-as-Judge evaluators • Build and maintain golden datasets for CI regression testing of AI pipelines • Lead or facilitate annotation workflows

🎯 Requirements

• BS in Computer Science, Statistics, Data Science, Information Science, Mathematics, Engineering, or a related quantitative field (MS or PhD preferred) • 5+ years of experience in data science, applied ML, information retrieval, or AI evaluation roles • Strong product sense • Statistical rigor • Information retrieval fundamentals • Proficiency with Python and SQL (Experience with Elixir is a plus) • Hands-on experience with LLMs • Data labeling and annotation experience • Strong written and verbal communication

🏖️ Benefits

• Competitive salary • Equity • Health insurance • Dental insurance • Vision insurance

Apply Now

Similar Jobs

🕒 February 24

NVIDIA

10,000+ employees

🏥 Healthcare

🏭 Manufacturing

🤖 Artificial Intelligence

AI Compiler Engineer optimizing deep learning and AI compiler for NVIDIA's inference solutions. Collaborating with teams to deliver high performance on AI workloads across various platforms.

🕒 February 24

BlueCloud

501 - 1000

💼 Consulting

📣 Marketing

📦 Logistics

Senior AI/ML Architect leading data platforms and GenAI solutions across Snowflake and AWS. Substantial experience in cloud environments and data engineering required.

🕒 February 23

Swans

11 - 50

⚖️ Legal

💼 Consulting

🤖 Artificial Intelligence

AI Specialist implementing practical AI solutions across client organizations. Engaging in client and internal projects to deploy effective AI capabilities and workflows.

🇺🇸 United States – Remote

⏰ Full Time

🟢 Junior

🟡 Mid-level

🤖 Artificial Intelligence

🚫👨‍🎓 No degree required

🕒 February 15

Team8

51 - 200

💼 Consulting

🏥 Healthcare

🏭 Manufacturing

Payment Accuracy and Concept Lead at Bluespine focused on detecting medical billing errors and fraudulent patterns. Collaborating with various teams to drive impactful results and create new audit concepts.

🇺🇸 United States – Remote

⏰ Full Time

🟠 Senior

🤖 Artificial Intelligence

🕒 February 13

CNA Insurance

5001 - 10000

🏗️ Construction

🏥 Healthcare

🏭 Manufacturing

AI Strategist shaping business outcomes through AI technology and managing multiple initiatives for strategic AI integration. Developing and executing AI frameworks aligned with ethical standards and company goals.

🇺🇸 United States – Remote

💰 $883k Post-IPO Equity on 2016-09

⏰ Full Time

🟡 Mid-level

🟠 Senior

🤖 Artificial Intelligence