Applied AI Engineer

About the role

You will build the AI agent capabilities that power Sapien's financial and operational intelligence. This involves designing novel architectures for reasoning over complex data, implementing verifiable agent workflows, and creating systems that learn and adapt to each company's unique operations.

Key responsibilities

• Design and implement agent architectures that enable observability, human‑in‑the‑loop verification, and precise context control across complex financial and operational workflows.
• Build library‑learning systems that reduce LLM dependencies by learning reusable patterns for planning, code generation, and data localization from customer interactions.
• Create graph‑based company representations and develop efficient search methods using embeddings, semantic clustering, and custom retrieval strategies.
• Develop multi‑modal parsers that unify diverse financial and operational data sources (Excel, ERPs, CRMs) into coherent, queryable schemas for agents.
• Design benchmarking and evaluation suites that quantify accuracy, reliability, and business impact across different customer workflows.

Required profile

• Strong algorithmic thinking demonstrated through ML research, competitive programming, mathematics, or building novel systems from scratch.
• Experience with modern agent frameworks, LLMs, and AI systems such as fine‑tuning, retrieval augmentation, tool use, or agentic architectures.
• Comfort working end‑to‑end: from prototyping research ideas to deploying production systems and iterating on real customer feedback.

Required skills

• Excel
• ERPs
• CRMs
• LLMs
• Embeddings
• Semantic clustering