Senior AI Engineer, Agents

WhyHireWrong?; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

WhyHireWrong? is seeking a hands-on AI engineer to advance production clinical AI agents within healthcare workflows. You will design clinical ontologies, fine-tune models, and build robust evaluation suites to catch edge cases that standard metrics miss.

You will work as an individual contributor, focusing on end-to-end model engineering, RAG-enabled retrieval, vector stores, and knowledge graphs to boost agent performance in real-world clinical scenarios.

Qualifications

• Based in Latin America and eligible to work in the region.
• Experience shipping and maintaining AI agents or LLM-based systems in production.
• Hands-on experience training, fine-tuning or distilling models end to end.
• Strong Python programming skills.
• Experience with context engineering (RAG, vector stores and knowledge graphs).
• A track record of shipping production systems; a background limited to academic or research work does not meet this requirement.
• Not currently in a management, director or VP role.

Responsibilities

• Design and maintain clinical ontologies used by production AI agents
• Train, fine-tune and distill language models end to end for clinical use cases
• Build and maintain evaluation frameworks that go beyond standard metrics to identify failure modes
• Ship and maintain AI agents and LLM based systems in production
• Apply context engineering methods, including RAG, vector stores and knowledge graphs, to improve agent performance

Skills

Python programming

Fine-tuning models

End-to-end model training

Context engineering

RAG

Knowledge graphs

Vector stores

AI production systems

Job description

About the company

A healthtech company building AI systems that work inside clinical workflows, supporting healthcare providers across Latin America.

About the role

This role exists to take the company's production clinical AI agents further. The person in this role will design clinical ontologies, fine-tune small language models, and build evaluation frameworks that catch failure modes standard metrics miss. This is an individual contributor role, not a path toward management.

Responsibilities

• Design and maintain clinical ontologies used by production AI agents
• Train, fine-tune and distill language models end to end for clinical use cases
• Build and maintain evaluation frameworks that go beyond standard metrics to identify failure modes
• Ship and maintain AI agents and LLM based systems in production
• Apply context engineering methods, including RAG, vector stores and knowledge graphs, to improve agent performance

Requirements

• Based in Latin America
• Experience shipping and maintaining AI agents or LLM based systems in production
• Hands on experience training, fine-tuning or distilling models end to end
• Strong Python programming skills
• Experience with context engineering, including RAG, vector stores and knowledge graphs
• A track record of shipping production systems; a background limited to academic or research work does not meet this requirement
• Not currently in a management, director or VP role