Senior LLM Engineer

Position Overview

SmartAsset is seeking an experienced Senior LLM Engineer to join our team and develop high-performance, scalable, and reliable LLM capabilities to power SmartAsset’s future. As a key member of our team, you will be responsible for designing and implementing LLM services and supporting logic, integrating services, and ensuring performance scalability, including handling hundreds of simultaneous users per second. We are looking for individuals passionate about building high-performance, scalable, and reliable LLM services and products with a track record of delivering solutions in AWS.

About SmartAsset

SmartAsset is an online destination for consumer-focused financial information and advice. Our mission is to help people make smart financial decisions, reaching over an estimated 59 million people each month (as of January 2025) through our educational content and personalized calculators and tools. To extend our mission, we also operate the SmartAsset Advisor Marketing Platform (AMP), which helps connect consumers with fiduciary financial advisors.

SmartAsset has earned recognition on the Inc. 5000 (#2574 in 2023) and Deloitte Technology Fast 500™ (#250 in 2022) lists. Currently, SmartAsset ranks on Y Combinator’s list of Top 100 Companies. A successful $110 million Series D funding round in 2021 valued the company at over $1 billion.

*Other than application and licensing fees, SmartAsset did not provide compensation for the aforementioned awards.

About the Team

At SmartAsset, you will join a team of data scientists, analysts, and ML engineers at the forefront of AI/ML application for the company. You will have the opportunity to work cross-functionally with leaders from different teams (Marketing, Product, Sales, and Technology) and with our growing Data team.

Responsibilities

• Design and implement a high-performance, scalable, and reliable LLM service using Python, LLM Services (e.g., OpenAI, Antropic’s Claude, Meta’s LLaMA, etc.), and AWS technologies to power our applications and business needs, including building services that can serve hundreds of concurrent users per second.
• Design and development of RAG pipelines.
• Building or integrating Voice related AI technologies and productizing at scale.
• Collaborate with business leaders to understand their needs and challenges, and identify potential LLM use cases.
• Design, develop, and deploy custom LLM solutions tailored to the requirements of different divisions, including co-creating prompts.
• Collaborate with the Data Science team to understand how to build the LLM solution, including fine-tuning OpenAI models as necessary.
• Implement software best practices to ensure seamless development, testing, and deployment of LLM solutions.
• Stay up-to-date with the latest advancements in LLM technologies and continuously explore ways to integrate these advancements into our existing solutions.
• Develop and maintain comprehensive documentation, including technical specifications, user guides, and best practices.
• Ensure data privacy and security compliance while working with LLMs.
• Provide technical support and training to internal teams as needed.
• Monitor LLM performance and make improvements to ensure acceptable response times based on use cases.
• Collaborate with other developers and data scientists within the organization to share knowledge, ideas, and best practices.
• Participate in code reviews and provide guidance to junior developers.

Skills/Experience You Have

• Proven experience with Cloud Platforms (AWS, GCP, or Azure).
• Hands-on experience working with Vector databases such as PineCone, Chroma, MongoDB, and LanceDB.
• Solid understanding of LLM concepts, such as prompt engineering, model fine-tuning, and transfer learning.
• Familiarity with one popular LLM framework (e.g., OpenAI GPT, Hugging Face Transformers).
• Minimum 5 years of experience in Python programming, with a strong focus on development.

Salary

• Information not provided.

Location Type

• Information not provided.

Employment Type

• Information not provided.