Senior Python Engineer

Summary

Join PandaDoc as a Sr. Python Engineer and contribute to the development of a powerful AI platform driving innovation across all products. This role involves building a scalable platform enabling AI-first products, tackling challenges like RAG pipelines and LLM routing, and ensuring reliable performance for thousands of customers. You will design, build, and deploy web systems and APIs, work with modern Gen-AI architecture, optimize multi-model support, and collaborate with various teams. The ideal candidate possesses extensive Python experience, real-world AI application experience, deep LLM knowledge, and end-to-end development skills. This position offers high ownership, a fast-paced environment, and the opportunity to create impactful solutions for small and medium-sized businesses.

Requirements

• Proficient in Python: 5+ years of experience coding in Python, building web systems, APIs, and scalable backend services
• Experience with real-world AI applications: You’ve worked on Gen-AI projects, including RAG, knowledge graphs, LLM routing, and fine-tuning. You understand the architecture and tools needed to make these systems work
• Deep knowledge of LLMs: You’ve worked with multiple LLM models and can explain their quirks, limitations, and how you’ve overcome them in past projects
• End-to-end development skills: You’ve developed systems from the ground up—from design and coding to deployment and testing
• Fast pace and high independence: You enjoy working in a fast-moving environment with lots of autonomy to solve problems and deliver results
• Product-focused mindset: You care about the impact of your work and strive to build systems that deliver tangible value to customers

Responsibilities

• Develop end-to-end systems: Design, build, and deploy web systems and APIs from scratch. Focus on building scalable, reliable solutions that integrate seamlessly with AI tools and workflows
• Work with modern Gen-AI architecture: Develop pipelines for RAG (retrieval-augmented generation), knowledge graphs, LLM routing, evaluation and testing frameworks, and fine-tuning models for specific use cases
• Optimize multi-model support: Work with multiple LLMs (like GPT-4, Claude, fine-tuned models) to ensure effective routing, dynamic task handling, and performance optimization
• Collaborate with product and engineering teams: Partner closely with technical PMs, designers, and other engineers to bring the platform to life and support innovation in AI products
• Solve real-world AI challenges: Apply your experience working with LLMs to navigate their quirks, troubleshoot issues, and build tools that ensure quality, scalability, and observability
• Move fast and iterate: Take ownership of your work, ship quickly, and learn from feedback to improve and optimize solutions