Senior AI Engineer – RAG & Reasoning Agents

We’re seeking a senior backend engineer with deep expertise in Retrieval-Augmented Generation (RAG), reasoning agents, and large-scale document retrieval systems. You’ll play a critical role in designing and scaling AI-powered systems that extract meaningful insights from massive datasets.

If you thrive in a fast-paced startup environment, enjoy solving complex AI infrastructure challenges, and are passionate about LLM-driven reasoning and retrieval, we want to hear from you.

Why Join PathPilot?

AI is transforming software development—code is being written faster than ever. But while building digital products is accelerating, understanding user behavior to improve them is still outdated and painful.

At PathPilot, we're on a mission to redefine how product teams learn from user behavior. We believe that AI should not only build products faster but also help refine and improve them seamlessly.

Join us early, work directly with the founders, and help shape the best tool for product engineers—an AI-powered assistant that turns session replays into actionable insights in real time. 🚀

What You’ll Do

• Architect and optimize RAG pipelines to efficiently retrieve, rank, and process information from large-scale document stores.
• Develop intelligent reasoning agents that can synthesize insights from retrieved data, improving response quality and reasoning depth.
• Implement scalable, event-driven backend systems using Node.js and Python to support high-throughput AI workloads.
• Fine-tune and deploy LLMs, optimizing them for reasoning over structured and unstructured data.
• Design retrieval systems using vector databases (e.g., Pinecone, Weaviate, FAISS) and hybrid search approaches.
• Optimize latency and performance for AI-driven document retrieval and generation at scale.
• Manage cloud deployments on AWS and/or Azure, ensuring resilience, fault tolerance, and observability.

What We’re Looking For

• 5+ years of experience in backend engineering, with expertise in Node.js and Python.
• Strong experience in RAG systems – designing and optimizing retrieval pipelines for massive datasets.
• Deep understanding of LLM-based reasoning, including prompt engineering, agent frameworks (e.g., LangChain, LlamaIndex), and long-context models.
• Hands-on experience with vector databases (e.g., Pinecone, Weaviate, FAISS) and hybrid search techniques.
• A track record of shipping fast, iterating frequently, and delivering real-world impact.

Bonus Points

• Background in knowledge graphs, embeddings optimization, or meta-learning for improved retrieval.
• Experience building high-throughput distributed systems that scale to millions of queries per day.
• Cloud deployment expertise (AWS) with CI/CD, monitoring, and auto-scaling best practices.
• Experience as a founder or founding engineer, comfortable taking ownership and making critical decisions.