Senior AI Engineer (Python & LLMs) | Remote | Portugal

A2IT Technology; Portugal; Remote; EUR 60,000 - 90,000; Full time

Job summary

A2IT Technology is seeking a Senior AI Engineer to design, build and optimise production-ready AI features with a strong focus on LLMs, RAG and AI agent orchestration. You’ll collaborate with the Head of Engineering, Backend Engineers and Software Architects to deliver secure, scalable and cost-efficient AI use cases.

We value proficiency in Python and backend frameworks (Django/FastAPI), hands-on RAG deployment, AI tooling, LLMOps, testing, and CI/CD.

Qualifications

• Strong experience with Python and backend development (Django/ FastAPI).
• Experience building production RAG systems with embeddings and vector search.
• Knowledge of AI agent orchestration frameworks (Google ADK, Haystack, LangGraph).

Responsibilities

• Design, build and maintain AI/LLM services and APIs using Python, Django and FastAPI.
• Develop end-to-end RAG pipelines, including chunking, embeddings, hybrid retrieval, reranking and vector databases.
• Build AI agents and tools using frameworks such as Google ADK, Haystack or LangGraph, including MCP-based tool calling.
• Implement LLMOps practices for tracing, evaluation, observability and optimisation of cost, latency and performance.
• Ensure code quality through automated testing, documentation, code reviews and CI/CD.
• Document AI components and ensure a structured knowledge transfer to the permanent team.

Skills

Python

Backend development

Django

FastAPI

RAG pipelines

LLMOps

API design

Testing

Tools

PostgreSQL

Redis

Celery

Docker

GitLab CI/CD

Job description

Please note: Candidates must be currently residing in Portugal.

Are you passionate about building reliable, production-ready AI solutions? We’re looking for a Senior AI Engineer to develop and optimise AI-powered features, with a strong focus on LLMs, Retrieval-Augmented Generation (RAG) and AI agent orchestration.

You’ll work closely with the Head of Engineering, Backend Engineers and Software Architect to deliver AI use cases that are secure, scalable, cost-efficient and ready for production.

What you’ll do

• Design, build and maintain AI/LLM services and APIs using Python, Django and FastAPI.
• Develop end-to-end RAG pipelines, including chunking, embeddings, hybrid retrieval, reranking and vector databases.
• Build AI agents and tools using frameworks such as Google ADK, Haystack or LangGraph, including MCP-based tool calling.
• Implement LLMOps practices for tracing, evaluation, observability and optimisation of cost, latency and performance.
• Ensure code quality through automated testing, documentation, code reviews and CI/CD.
• Document AI components and ensure a structured knowledge transfer to the permanent team.

What we’re looking for

• Strong experience with Python and backend development, particularly Django and FastAPI.
• Hands‑on experience building production RAG systems, including vector search, embeddings and reranking.
• Practical knowledge of AI agent orchestration frameworks (Google ADK, Haystack or LangGraph), prompt engineering and MCP.
• Experience with LLMOps, ideally including Langfuse, evaluation methodologies and token/cost optimisation.
• Familiarity with PostgreSQL, Redis, Celery, Docker and GitLab CI/CD.
• Experience with OpenAPI, pytest, database migrations and modern Python tooling such as uv and ruff.

If you have a strong AI engineering background and enjoy turning LLM capabilities into reliable, production-ready solutions, we’d love to hear from you!

Interested or know someone who could be a great fit? Get in touch or share this opportunity.