Applied AI Scientist

Tipalti; United States; Remote; USD 120,000 - 190,000; Full time

Job summary

Tipalti seeks a middle-level Applied AI Scientist to develop AI agents that automate workflows across sales, customer success, and support in a fintech setting. You will own end-to-end architecture, ensuring robust tooling and processes for production deployment.

You will design and maintain retrieval-augmented generation (RAG) systems leveraging Tipalti's knowledge base, while continuously evaluating agent performance against defined metrics and real-world feedback.

Qualifications

• Mid-level Applied AI Scientist with strong AI/ML engineering background.
• Experience deploying AI solutions in production is a plus.
• Familiarity with fintech context is advantageous.

Responsibilities

• Design and deploy AI agents to automate workflows across business functions such as sales, customer success, and support.
• Build and maintain retrieval-augmented generation (RAG) systems using the company knowledge base.
• Define metrics, evaluate agent performance, and iterate based on data and stakeholder feedback.

Skills

AI/ML engineering

Deployment of AI solutions

Tools

RAG systems

Job description

Tipalti seeks a middle-level Applied AI Scientist to develop AI agents that enhance business operations in a fintech context. Candidates with a strong background in AI/ML engineering, particularly in deploying AI solutions, should consider applying.

In this role, you will design and deploy AI agents that automate workflows across various business functions such as sales, customer success, and support. You'll be responsible for the end-to-end architecture of these agents, ensuring they are equipped with the necessary tools and processes for effective operation in a fintech environment.

You will also build and maintain retrieval-augmented generation (RAG) systems that utilize Tipalti's proprietary knowledge base. Continuous evaluation and improvement of agent performance will be key, as you define metrics for success and iterate based on real-world data and feedback from stakeholders.