Product Engineer

Staff Product Engineer

We're hiring a Staff Product Engineer - someone who takes a feature from idea to production with full ownership. A builder, not a reviewer. This role sits at the intersection of backend systems, product experience, and AI. You'll own complete product surfaces - APIs, data pipelines, and the LLM orchestration layer that ties it all together - and work directly with the founders to shape what gets built. If you close the gap between what's built and what customers actually need, this is for you.

What You'll Build

• Own features end-to-end: scoping, architecture, implementation, and iteration based on user feedback
• Build backend systems powering AI-driven workflows — Python, FastAPI, PostgreSQL, Redis
• Ship LLM-native features: RAG pipelines, agentic workflows, prompt systems that operate on real data infrastructure
• Work on developer-facing surfaces: VS Code extensions, CLI tooling, dbt integrations, SQL intelligence
• Improve reliability and performance of production AI systems at scale
• Partner directly with founders and early customers to decide what to build next

What We're Looking For

Must have

• 8+ years building production systems
• Strong backend fundamentals - Python (or similar), APIs, distributed systems, databases
• LLM in production: RAG, agents, prompt pipelines
• Product instinct: you've pushed back on specs, rewritten requirements, and been right
• Startup DNA: you've set direction, not just executed it

Strong plus

• Experience with dbt, Airflow, Spark, or data platform tooling
• Familiarity with SQL parsing, ASTs, or data lineage
• TypeScript / React experience for full-stack ownership
• Former founder or early founding engineer

Projects You'll Work On:

• Advanced AI Agent Architecture: Design and implement sophisticated multi-agent systems that can understand context, make decisions, and enable seamless collaboration between AI and human data professionals.
• Large-Scale RAG Systems: Build and optimize retrieval-augmented generation pipelines that can efficiently process and utilize enterprise-scale knowledge bases.
• Model Optimization & Deployment: Implement advanced techniques (LoRA, Prompt Tuning) to adapt off-the-shelf models for specific enterprise data tasks, ensuring faster, more accurate performance.
• Scalable AI Infrastructure: Develop and optimize cloud-native architectures (AWS, Kubernetes) for large-scale training, inference, and multi-agent orchestration.
• Enterprise Security & Compliance: Implement robust security measures for LLM applications, including data anonymization, prompt injection prevention, and compliance with enterprise security standards.

What We Offer

• Competitive salary and equity
• Access to cutting-edge AI infrastructure and resources
• Team offsite and opportunities to attend and present at leading industry conferences (across the world)
• Learning budget for AI courses, books, and computing resources
• Dynamic and intellectually stimulating work environment with a team of talented engineers
• Opportunities to shape the direction of the company and leave a lasting impact