AI Developer

remoting.work; United States; Remote; USD 150,000 - 190,000; Full time

Job summary

remoting.work is seeking an AI Engineer to build and operate a single-tenant platform for a professional services team. You own backend, APIs, orchestration, retrieval, pipelines and security, spanning from build to operation.

You will implement session management, agent routing, embeddings, and integrations with Microsoft Graph and other enterprise APIs while maintaining auditability and deterministic components. Remote work from outside North America is supported for this ongoing role.

Qualifications

• Five+ years of software engineering experience, incl. 2+ years building AI/LLM-powered apps.
• Proven track record taking a system from build to production operation.
• Bachelor's degree in CS or related field, or equivalent practical experience.
• Experience in legal, financial or compliance-sensitive domains is a plus.

Responsibilities

• Build the backend and APIs in Python and FastAPI.
• Implement API gateway, authentication and role-based authorization.
• Build session management, approval queues and scheduled jobs.
• Design agent orchestration and routing across multiple personas.
• Implement retrieval over a trusted document corpus with citation verification.
• Build and tune embeddings, prompts and evaluation rubrics.
• Integrate speech-to-text and text-to-speech for voice note workflows.
• Build the document engine: PDF assembly, stamping, OCR and generation.
• Create a rule-driven deadline and task engine with audit log.
• Ingest transcripts and structured extraction pipelines.
• Integrate Microsoft Graph and other APIs; own infra, CI/CD, IaC.
• Implement logging, tracing, cost metering and encrypted backups.
• Operate and evolve the system after launch with model upgrades.

Skills

Python

FastAPI

LLM apps

PostgreSQL

Redis

Docker

Cloud/CI-CD

API integration

Security

React/TypeScript

Education

Bachelor's degree in Computer Science

Tools

pgvector

Redis

Job description

Job Overview

We are seeking an AI Engineer to build and operate a single-tenant AI platform supporting a professional services team. This is the continuous role spanning the entire system: backend and APIs, agent orchestration, retrieval, document and task pipelines, integrations, infrastructure and security. The engagement is ongoing, continuing past the initial build into operation and iteration. This position is with a USA- and Canada-based employer and is open to qualified candidates working remotely from outside North America.

About The Company

An established family law practice in the northeastern United States, with multiple offices and a team of attorneys, mediators and support staff serving clients across the region. The firm is known for a client-centered approach built on care, integrity and dedication, and is now investing in purpose-built technology to support its legal and administrative teams.

Ideal Candidate

You are an engineer who has taken AI systems from prototype to production and kept them running. You are careful about correctness: you know which parts of a system must be deterministic and tested rather than model-generated, and you design for auditability and human approval by default. You work independently, own the full stack, and communicate plainly with non-technical stakeholders.

Key Responsibilities

Platform and Backend

• Build the backend and APIs in Python and FastAPI.
• Implement the API gateway, authentication and role-based authorization.
• Build session management, approval queues and scheduled jobs.

AI and Retrieval

• Build the agent orchestration and routing layer across multiple assistant personas.
• Implement retrieval over a trusted document corpus with citation verification.
• Build and tune embeddings, prompts and evaluation rubrics.
• Integrate speech-to-text and text-to-speech for voice note workflows.

Pipelines and Engines

• Build the document engine: PDF assembly, stamping, OCR and document generation.
• Build a rule-driven deadline and task engine with cascading date logic and an audit log.
• Build transcript ingestion and structured extraction pipelines.

Integrations and Operations

• Integrate Microsoft Graph for mail, calendar and tasks, plus CRM, ads and research platform APIs.
• Own infrastructure, containerized deployment, continuous integration and infrastructure as code.
• Implement logging, tracing, cost metering and encrypted backups.
• Operate and evolve the system after launch, including model upgrades and new features.

Skill Sets Required / Preferred

Technical Skills

• Strong Python, with production experience in FastAPI or a similar async framework.
• Hands-on experience building LLM applications: orchestration, retrieval augmented generation, prompt design and evaluation.
• PostgreSQL, including vector search with pgvector, and Redis for queues and sessions.
• Experience with Docker, cloud infrastructure, CI/CD and infrastructure as code.
• API integration experience, ideally with Microsoft Graph or similar enterprise platforms.
• Security-minded design: least privilege, encryption, credential management and audit logging.
• Familiarity with React and TypeScript, enough to maintain a front end after handover, is preferred.

Soft Skills

• Strong ownership and independent judgment as the sole engineer on the system.
• Clear communication with non-technical stakeholders.
• Disciplined about testing and correctness in high-stakes workflows.
• Comfortable prioritizing and sequencing work across a long-running build.

Experience & Education

• Five or more years of software engineering experience, including two or more years building AI or LLM-powered applications.
• Demonstrated experience taking a system from build through to production operation.
• Bachelor's degree in Computer Science or a related field, or equivalent practical experience.
• Experience in legal, financial or other compliance-sensitive domains is a plus.