Posted in

Principal Software Engineer – Generative AI Application

Principal Software Engineer – Generative AI Application

CompanyRadian
LocationSalt Lake City, UT, USA, Villanova, PA, USA, Philadelphia, PA, USA, Pittsburgh, PA, USA, Denver, CO, USA
Salary$133300 – $190500
TypeFull-Time
DegreesBachelor’s
Experience LevelSenior

Requirements

  • Bachelor’s Degree or Equivalent Experience
  • 5 years of prior work related experience
  • Professional experience with React, Node.js and/or Professional experience with Python, JavaScript/TypeScript, C# and Java
  • Experience with designing, implementing web application and consuming RESTful APIs in AWS/Azure
  • Experience with Python development, demonstrating a deep understanding of the language and its best practices
  • Experience with LLM tools and frameworks such as OpenAI, Claude, Bedrock, prompt engineering, LangChain, LlamaIndex and etc.
  • Experience with the machine learning process of retrial augmented generation (RAG), fine-tuning and MLOps
  • Proficiency in working with RDBMS and No-sql, showcasing the ability to design and optimize database structures
  • Proficiency in working with vector database
  • A solid understanding in foundation models, custom model training and its lifecycle management
  • Understanding of DevOps processes and you appreciate the value technologies like Serverless, containers and Kubernetes bring to the software deployment and development process
  • Experience with performance and optimization problems and a demonstrated ability to both diagnose and prevent these problems
  • Demonstrated capacity to clearly and concisely communicate about complex technical, architectural, and/or organizational problems and propose thorough iterative solutions.

Responsibilities

  • Develop features and improvements utilizing generative AI technologies and solutions to the Radian products in a secure, well-tested, and performant way.
  • Work with Product Management and other stakeholders (Backend, UX, etc.) to iterate on new features.
  • Write code that meets our internal standards for style, maintainability, and best practices for a high-scale web environment. Maintain and advocate for these standards through code review.
  • Demonstrate capacity to clearly and concisely communicate about complex technical, architectural, and/or organizational problems and propose thorough iterative solutions.
  • Propose initial technical implementations which support architectural changes that solve scaling and performance problems.
  • Confidently ship immense or otherwise extremely high-impact features and improvements with minimal guidance and support from other members of the organization.
  • Interact with customers and other external stakeholders as a consultant and spokesperson for the work of your sub-department.
  • Teach, mentor, grow, and provide advice to other domain experts, across several teams in their department.
  • Perform other duties as assigned or apparent.

Preferred Qualifications

  • Experience with LLM tools and frameworks such as OpenAI, Claude, Bedrock, prompt engineering, LangChain, LlamaIndex and etc.
  • Experience with the machine learning process of retrial augmented generation (RAG), fine-tuning and MLOps.
  • Proficiency in working with RDBMS and No-sql, showcasing the ability to design and optimize database structures.
  • Proficiency in working with vector database.
  • A solid understanding in foundation models, custom model training and its lifecycle management.
  • Understanding of DevOps processes and you appreciate the value technologies like Serverless, containers and Kubernetes bring to the software deployment and development process.