We are seeking a production-oriented AI Software Engineer to build and maintain the systems that power our intelligent feedback analysis platform. This role focuses on two critical technical areas: implementing Retrieval-Augmented Generation (RAG) systems for intelligent feedback analysis and developing data processing pipelines that handle millions of user feedback records daily.
This position requires strong production engineering capabilities. System reliability directly impacts our customers, necessitating an engineer who writes robust, maintainable code and possesses the technical depth to diagnose and resolve complex issues efficiently. You will collaborate closely with our engineering team to ensure our AI-powered features operate reliably at scale.
Responsibilities
The role centers on two interconnected areas of work. Depending on your technical strengths, 70% to 80% of your time will focus on the area where you demonstrate greater expertise, with the remainder devoted to the secondary area. Both skill sets are required, but we recognize that individual backgrounds vary in emphasis.
For engineers with stronger RAG system expertise:
Design, build, and maintain end-to-end RAG implementations that retrieve relevant context from millions of feedback records.
Implement and optimize vector database solutions for semantic search.
Develop chunking strategies that balance context quality with system performance.
Debug retrieval quality and generation reliability issues.
Integrate with large language model APIs, implementing proper error handling, retry logic, and cost management strategies.
Support the data processing pipelines that feed these RAG systems (secondary responsibility).
For engineers with stronger data pipeline expertise:
Build and maintain ETL pipelines that process more than 10 million feedback records daily.
Write Python code for data transformations and processing logic.
Optimize existing pipeline performance when bottlenecks emerge.
Implement data quality checks and validation logic.
Design and refine data models and schemas that support both analytical workloads and AI feature requirements.
Troubleshoot production issues when pipelines fail or produce incorrect results.
Enhance monitoring to catch data quality problems early.
Support RAG system implementation and optimization (secondary responsibility).
Regardless of focus area, the work requires writing robust Python code that handles edge cases gracefully, understanding how to work with data at scale, and maintaining systems that customers depend upon for accurate, timely insights.
Requirements:
5+ years of production software engineering experience, with Python as the primary programming language.
Hands-on experience building or maintaining RAG systems in production environments, including practical work with vector databases, embeddings, and retrieval strategies.
Proven track record working with large-scale data processing pipelines handling millions of records.
Ability to discuss lessons learned from production incidents and system optimizations.
Strong SQL proficiency and practical experience with data modeling for analytical workloads.
Production debugging expertise, including experience responding to production incidents and implementing systematic troubleshooting approaches.
Bachelor’s or Master’s degree in Computer Science, Engineering, or a related technical discipline, or equivalent practical experience.
Self-driven with the ability to take ownership of systems end-to-end while collaborating effectively with cross-functional teams.
Preferred Qualifications:
Experience with AI orchestration frameworks such as LangChain, LangGraph, or similar tools.
Prior work with vector databases, including Pinecone, Weaviate, Chroma, or comparable systems.
Experience deploying and managing services on cloud platforms such as AWS or GCP, along with containerization experience using Docker.
Background in prompt engineering and optimizing large language model behavior.
Familiarity with data visualization and analytics tools.
