Senior AI Engineer

Senior AI Engineer, AI Platform & LLM Systems

Compensation: Senior: ~$220k–$240k base | Significant equity

Location: San Francisco, hybrid

Employment Type: Full-time

A fast-scaling, well-funded B2B SaaS company building AI-native software for complex, high-value professional workflows.

This team is rethinking how highly skilled professionals interact with complex data, documentation, and knowledge-heavy processes. Following significant recent funding and continued commercial growth, AI has become a central part of the company’s product and engineering strategy.

Rather than adding lightweight AI features around an existing product, the engineering organization is investing heavily in the underlying platform required to make production AI reliable: evaluation, ingestion, observability, retrieval, orchestration, and the infrastructure supporting increasingly capable AI workflows.

What You’ll Do

• Build and scale core AI platform capabilities across evals, ingestion, observability, retrieval, and AI/ML infrastructure
• Own AI systems end-to-end, taking ideas from prototype through to reliable production deployments
• Design and improve RAG pipelines, embedding workflows, prompt systems, retrieval strategies, and model interaction patterns
• Develop infrastructure for evaluating, monitoring, versioning, and improving LLM-powered systems
• Build tooling around AI workflow orchestration, quality control, experimentation, and production reliability
• Work with complex, domain-specific datasets to improve retrieval and model performance
• Partner closely with product, design, engineering, and subject-matter experts to turn sophisticated workflows into usable AI products
• Help establish technical patterns and engineering standards for applied AI across the wider organization

What You’ll Bring

• Strong software engineering experience across areas such as backend engineering, distributed systems, infrastructure, developer platforms, or ML systems
• Strong hands-on Python engineering skills
• Experience shipping AI or ML systems into production rather than working exclusively on prototypes or research
• Practical experience with one or more of LLMs, RAG, NLP, AI agents, model evaluation, observability, data ingestion, or AI/ML infrastructure
• Strong understanding of software architecture, system design, reliability, and production engineering
• Ability to operate comfortably across both AI-specific problems and traditional software engineering challenges
• A high bar for engineering quality, including the ability to critically review AI-generated code rather than treating generated output as production-ready
• A pragmatic builder mentality and an appetite for high ownership in a fast-moving technical environment

Tech Stack

• Python
• LLMs / Generative AI
• Retrieval-Augmented Generation (RAG)
• Embeddings & semantic retrieval
• LLM evaluation frameworks
• AI observability & monitoring
• Data / document ingestion pipelines
• Workflow orchestration
• AI / ML infrastructure
• Distributed backend systems

Why Join?

This is an opportunity to join at an important inflection point: the company has strong funding, an established product and customer base, and executive-level commitment to making AI a fundamental part of the platform.

You’ll have significant ownership over the infrastructure that determines whether AI systems actually work in production, from how information enters the system and is retrieved, through to how outputs are evaluated, monitored, and continuously improved.