Applied AI Engineer: Orchestrate Trusted Family Care Agents

Mantle; San Francisco (CA); Hybrid; USD 130,000 - 200,000; Full time

Benefits offered by this job

Remote Fridays

Job summary

Mantle is building an AI agent to help families manage aging parents. As a Software Engineer on the Applied AI team, you will design and build agent systems that take real work off families’ plates, understanding situations, acting on them, and escalating when needed.

You will work with founders and the engineering team to move capabilities from prototype to production, focusing on evals, failure cases, and dependable agent behavior for daily use.

Qualifications

• 2–10 years building production software with modern technologies.
• Hands-on experience shipping LLM-powered features or agents to real users.
• Strong grasp of prompt design, retrieval, tool calling and agent orchestration patterns.
• Experience building evaluation systems and using them to drive product decisions.
• Strong backend skills (e.g. Python or Node.js, APIs, data pipelines) and experience deploying on AWS.

Responsibilities

• Design and build the agent systems that understand families' situations, take actions, and know when a human should step in.
• Collaborate with founders and the engineering team to take agent capabilities from prototype to production.
• Build evals, identify failure cases, and improve agent reliability.
• Develop retrieval and memory systems to surface the right context for each family at the right time.
• Create integration layers connecting AI models, third-party services and internal systems into cohesive user experiences.

Skills

LLM features

Prompt design

Agent orchestration

Python/Node.js

AWS deployment

Tools

Cursor

Claude Code

AWS

Job description

Mantle is building an AI agent to help families manage aging parents. As a Software Engineer on the Applied AI team, you will design and build agent systems that take real work off families’ plates, understanding situations, acting on them, and escalating when needed.

You will work with founders and the engineering team to move capabilities from prototype to production, focusing on evals, failure cases, and dependable agent behavior for daily use.