Staff Software Engineer, Applied AI

About the Role

We're building AI products that solve real problems for real customers. This role sits at the intersection of product and engineering– you'll own features end-to-end, from understanding user problems to shipping production code that scales.

Applied AI product engineering is a new discipline. You won't just be integrating APIs – you'll be designing AI systems that work reliably in production, building evaluation frameworks to measure quality, and iterating rapidly based on real user feedback. You'll work directly with customers to understand their workflows and translate that understanding into product decisions.

This is not a research role. We're looking for engineers who ship. You'll be measured by the products you deliver and the problems you solve, not by papers published or models trained. The best candidates combine deep technical skills with strong product intuition and a relentless focus on user outcomes.

What You'll Do

• Design, build, and ship AI-powered product features from concept through production deployment
• Develop and maintain LLM-based systems including RAG pipelines, agents, and workflow automation
• Build evaluation frameworks and monitoring systems to ensure AI quality and reliability
• Work directly with customers to understand problems, gather feedback, and validate solutions
• Collaborate with product and design to define roadmap and prioritize features based on impact
• Optimize system performance, cost, and latency as usage scales
• Contribute to technical architecture decisions and establish engineering best practices

Qualifications

• 4+ years of software engineering experience, with at least 1-2 years building AI/ML-powered products
• Strong proficiency in Python; experience with TypeScript/JavaScript for full-stack development
• Hands-on experience with LLMs in production: prompt engineering, RAG systems, fine-tuning, or agent frameworks
• Solid understanding of ML fundamentals: embeddings, vector databases, evaluation metrics, and model selection
• Experience building and maintaining production systems with high reliability requirements
• Strong product intuition, ability to translate ambiguous user needs into concrete technical solutions
• Excellent communication skills and comfort working directly with customers and stakeholders
• BS/MS in Computer Science, or equivalent practical experience

Nice to Have

• Experience with AI infrastructure: LangChain, LlamaIndex, vector databases (Pinecone, Weaviate, Chroma)
• Background in NLP, information retrieval, or search systems
• Previous startup experience, especially as an early engineer or technical co-founder
• Domain expertise in financial services, legal, healthcare, or other enterprise SaaS verticals
• Contributions to open-source AI/ML projects
• Experience building developer tools or platforms