Remote Applied AI Engineer — Build AI Agents

Devconnectplatform; United States; Remote; USD 215,000 - 250,000; Full time

Benefits offered by this job

Health coverage

401(k) plan

Remote-first employment

Wellness stipend

Flexible PTO

Learning & development budget

Future membership

Equity

Job summary

Future PLC is seeking an Applied AI Engineer to build and ship AI-powered features that enhance product experience and business outcomes. You will own the full lifecycle from concept to production, focusing on scalable, efficient, and reliable AI services that perform at scale.

You’ll collaborate across product, mobile, and backend teams to prototype, evaluate, and deploy AI capabilities, balancing performance, cost, and quality to deliver real user value.

Qualifications

• Strong Python skills with production deployments.
• Experience with LangChain/LangGraph or similar agent frameworks.
• Hands-on experience deploying and evaluating LLM-powered features.
• Comfort with async Python, HTTP APIs, and streaming protocols.
• Experience designing data validation schemas (Pydantic, JSON Schema).
• Ability to debug across layers from LLM calls to infrastructure resources (Terraform).
• Strong cross-functional communication with product, mobile and backend teams.

Responsibilities

• Build and ship AI agents serving real users with tool-calling LLMs.
• Design evaluation harnesses and quality rubrics for safety and personalization.
• Prototype, validate, and deploy agent capabilities across staging and production.
• Improve reliability, latency, and cost via caching, budgets, and observability.
• Implement API integrations with validation, local data search, and structured submissions.

Skills

Python

LangChain/LangGraph

LLMs in production

Async Python

HTTP APIs

Streaming protocols

Pydantic

JSON Schema

Terraform

Tools

AWS

Langfuse

OpenTelemetry

Datadog

Job description

Future PLC is seeking an Applied AI Engineer to build and ship AI-powered features that enhance product experience and business outcomes. You will own the full lifecycle from concept to production, focusing on scalable, efficient, and reliable AI services that perform at scale.

You’ll collaborate across product, mobile, and backend teams to prototype, evaluate, and deploy AI capabilities, balancing performance, cost, and quality to deliver real user value.