Remote Applied AI Engineer, Conversational AI

Paires; United States; Remote; GBP 106,000 - 176,000; Full time

Benefits offered by this job

Fully remote

Job summary

Paires is hiring an Applied AI Engineer to own the conversation layer of an AI-first fundraising platform. You will design and maintain agents that handle replies, booking, nurture, and relationships across warm outreach, investor network, and investor relations.

This role focuses on production systems, not a research project. You will build end-to-end conversational agents, from inbound messages to human-in-the-loop approvals, and create broader applied-AI features such as classification,

Qualifications

• Ship conversational LLM systems to production with real users.
• Built evals from scratch: golden sets, judge criteria, and decisions based on metrics.
• Integrated LLMs with email, CRM, or messaging systems.
• Think like an operator and align messaging with business goals.
• Engineer-first approach; balance 80/20 between engineering and research.

Responsibilities

• Own agents that read inbound messages and draft the right reply, fast, with a human in the loop.
• Own the messaging layer across our warm outreach, investor network, and investor relations.
• End-to-end conversational agents: replies, booking, nurture, and support that reads human.
• Develop the eval spine that gates quality with golden sets and guardrails.
• Broaden applied-AI features: classification, extraction, routing, summarization.

Skills

LLM systems

Eval design

CRM integration

Operational mindset

Engineering focus

Tools

Python

Supabase

Pydantic AI

Claude Agent SDK

AWS

Job description

Paires is hiring an Applied AI Engineer to own the conversation layer of an AI-first fundraising platform. You will design and maintain agents that handle replies, booking, nurture, and relationships across warm outreach, investor network, and investor relations.

This role focuses on production systems, not a research project. You will build end-to-end conversational agents, from inbound messages to human-in-the-loop approvals, and create broader applied-AI features such as classification,