AI Engineer

Remote Crew; Portugal; Remote; EUR 90,000 - 130,000; Full time

Job summary

Remote Crew is seeking a Senior AI Engineer to own the intelligence layer of a compliant cloud orchestration platform. You will architect autonomous AI agents that operate across AWS, Azure, and GCP, turning black-box AI into predictable, type-safe enterprise tools.

You'll build scalable microservices in Python and Go, apply LangChain/LangGraph, and implement observability via LangSmith. This role emphasizes compliance, reliability, and hands-on leadership in AI engineering.

Qualifications

• 5+ years in backend engineering or full-stack data science with production AI agents/LLM apps.
• Hands-on experience with PydanticAI and/or LangChain/LangGraph.
• Proven use of LangSmith or similar tools to evaluate model performance and datasets.
• Deep Python (FastAPI/Pydantic) and/or Go for scalable microservices wrapping AI logic.
• Strong data science foundations: EDA and ML modeling.
• Solid understanding of AWS/Azure/GCP and Terraform.

Responsibilities

• Design AI agent architectures using PydanticAI and LangGraph.
• Develop backend services in Python/Go integrating LangChain tools with infrastructure.
• Own monitoring and evaluation with LangSmith for enterprise reliability.
• Implement RAG pipelines and fine-tuning for technical contexts.
• Apply rigorous validation to keep AI within compliance boundaries.
• Contribute to core engine, participate in architecture reviews, mentor teammates.
• Ground decisions in user/model data analyses balancing performance and cost.

Skills

Python

Go

API design

ML foundations

LangChain/LangGraph

LangSmith

Tools

FastAPI

PydanticAI

Terraform

AWS

Azure

GCP

Job description

Remote Crew is seeking a Senior AI Engineer to own the intelligence layer of a compliant cloud orchestration platform. You'll architect and deploy autonomous AI agents that manage global cloud footprints across AWS, Azure, and GCP, turning black-box AI into predictable, type-safe enterprise tools. This role combines agentic engineering mastery with production-grade observability, requiring someone who can build scalable microservices that wrap AI logic while maintaining strict compliance boundaries and enterprise reliability.

Location: Remote (Portugal, Spain)

What You'll Do

• Design and implement robust AI agent architectures using PydanticAI for structured reasoning and LangGraph for complex, cyclic state machine workflows
• Develop backend services in Python and Go that integrate LangChain ecosystem tools with real-world infrastructure, enabling agents to reason, tool-call and self-correct
• Own the monitoring and evaluation lifecycle using LangSmith, building pipelines to trace, debug and optimize agentic chains for enterprise-grade reliability
• Implement RAG pipelines and fine-tuning strategies to ensure agents understand deep technical contexts like Terraform plans and OPA policies
• Use rigorous validation to ensure AI agents operate within strict compliance boundaries, turning unpredictable AI into deterministic enterprise tools
• Contribute directly to the core engine, participate in architecture reviews and mentor the engineering team on AI best practices
• Ground technical decisions in user and model data analyses, balancing performance, cost and real user impact

What We're Looking For

• 5+ years in backend engineering or full-stack data science profile with strong focus on deploying AI agents or LLM-powered applications in production
• Deep hands-on experience with PydanticAI and/or LangChain/LangGraph
• Proven track record using LangSmith or similar tools (Arize, LangFuse) to evaluate model performance, debug complex traces and manage datasets for continuous improvement
• Deep expertise in Python (FastAPI/Pydantic) and/or Go, able to build scalable microservices that wrap AI logic
• Strong data science and machine learning foundations: EDA and fundamental/classical ML modeling
• Solid understanding of AWS/Azure/GCP and Infrastructure-as-Code (Terraform)
• Product-minded approach: you build products, not just models, caring about latency, cost and whether the agent solves the user's problem
• Comfortable working in non-bureaucratic environments, leading through technical excellence and mentorship
• Experience with LLMs as a judge for evaluation and continuous improvement - nice to have
• Cloud automation and DevSecOps context - nice to have
• Direct access to leadership to shape AI strategy - nice to have