Could AI Engineer

Team: Backend

Location: US, Latin America, Argentina, Buenos Aires, Mexico, Mexico City, Colombia, Bogota

Commitment: Full-time: Remote

Workplace Type: remote

Responsibilities

Work closely with Legal, Compliance, and the MLRO to support internal compliance policy reviews, files delivery, remediation tracking, and technical support.
Track compliance-related requirements for new product and service launches, and coordinate action items with relevant stakeholders.
Partner with Legal and Compliance teams to identify, design, and implement AI-driven solutions that improve the efficiency and scalability of compliance and legal operations.
Used the enhance intelligent systems leveraging LLMs, RAG, agentic workflows, long-term memory, tool use, subagents, and multi-agent architectures for handling law files.
Develop benchmark frameworks and evaluation methodologies for legal and compliance AI systems, including benchmark dataset construction, annotation strategy design, and performance measurement.
Continuously evaluate and improve systems across retrieval quality, latency, groundedness, factuality, and task success metrics.
Conduct independent research and rapidly prototype new ideas to solve ambiguous legal and compliance workflow challenges.
Support related administrative and operational activities in accordance with company compliance requirements.

Requirements

• 5 years of relevant experience in compliance technology, legal technology, regulatory technology, or software/application development supporting compliance or legal functions.
• Strong understanding of relevant compliance rules, regulations, and day-to-day compliance operations.
• Bachelor’s degree required; background in AI, Computer Science, Engineering, Law, or related disciplines preferred.
• Hands-on experience building production RAG systems, including embeddings, vector databases, hybrid search, reranking, chunking strategies, text preprocessing, and multimodal parsing.
• Experience implementing advanced Agentic RAG approaches such as Self-RAG, Corrective RAG, adaptive retrieval, and multi-hop reasoning workflows.
• Strong understanding of LLM and agent fundamentals, including prompt engineering, context engineering, memory, planning, tool use, MCP, and multi-agent systems.
• Demonstrated ability to conduct independent research, solve ambiguous problems, and rapidly prototype practical solutions.
• Strong written and verbal communication skills.
• Bilingual English/Mandarin is preferred to be able to coordinate with overseas partners and stakeholders.