Senior AI Engineer, AI Forge – AWAKE Studio

Making Science Group S.A.; Madrid; On-site; EUR 70,000 - 95,000; Full time

Benefits offered by this job

Indefinite contract

Performance bonus

Flexible payment plan

Transportation & meal tickets

International team & Ambassadors

Job summary

Making Science is an international digital acceleration company. You will join the AI Forge engine within AWAKE Venture Studio, building and scaling AI-powered solutions in a high-performance team alongside the CEO and researchers.

The role focuses on rapid prototyping, production-grade systems, and cutting-edge model evaluation. You will prototype with Python (FastAPI), design advanced retrieval and multi-agent workflows, and deploy MLOps on GCP with Vertex AI, GKE, and Cloud Run.

Qualifications

• Proven AI production track record shipping LLM applications and Generative AI solutions.
• Deep Python expertise with packaging and testing tools (Poetry, Pytest).
• Data and semantic engineering with rapid experimentation, embedding generation, and hybrid search.
• Cloud infrastructure, containerization (Docker), and Infrastructure as Code (Terraform).
• Thrive in fast-paced startup or venture builder environments with autonomy.

Responsibilities

• Build & prototype from scratch using Python (FastAPI).
• Develop advanced retrieval systems (RAG/GraphRAG) with Neo4j and vector databases like Qdrant, Pinecone, or pgVector.
• Orchestrate multi-agent workflows and model routing using LangGraph, LangChain, LlamaIndex, and MCP.
• Deploy & scale MLOps on Google Cloud Platform (GCP) with Vertex AI, GKE, and Cloud Run.
• Evaluate state-of-the-art models (OpenAI, Anthropic, Gemini, Llama) for feasibility and roadmaps.
• Ensure security & compliance following information security best practices.

Skills

AI production

Python expert

Data & semantic eng

DevOps

Adaptability

Tools

Docker

Terraform

Job description

Making Science is an international digital acceleration company. You will join the AI Forge engine within AWAKE Venture Studio, building and scaling AI-powered solutions in a high-performance team alongside the CEO and researchers.

The role focuses on rapid prototyping, production-grade systems, and cutting-edge model evaluation. You will prototype with Python (FastAPI), design advanced retrieval and multi-agent workflows, and deploy MLOps on GCP with Vertex AI, GKE, and Cloud Run.