CDI - Senior Context & Analytics Engineer - Paris

Mission

An agent is only as good as the data and knowledge on which it responds. Pipelines, data models, metric definitions, access rights: you create and govern this foundation, and our clients' applications and agents rely on it. When an analyst or agent asks for a figure, the answer is that of the finance team, accompanied by its definition and source.

This position is for you if you want business units and agents to be able to trust data and use it.

Artefact supports the world's largest companies in deploying AI: 3,000 AI makers in over 30 countries, over 1,000 clients. In France, the Engineering department brings together about 300 people under the responsibility of the CTO; here you will join the AI Applied Engineer chapter, the Context & Analytics Engineer archetype.

Activities and responsibilities

With business teams and analysts, the goal is to define what each metric means and to ensure that the data corresponds to it. On this foundation, Product Engineers and AI Engineers build applications and agents.

Platform Engineers operate the infrastructure on which your pipelines run. Interactions with the client's data owners and governance teams, peer code reviews, and mentoring new hires complete the daily tasks.

Your responsibilities:

• Build ingestion pipelines and data models, using dbt for example.
• Implement data quality controls and maintain lineage.
• Build the semantic layer and metric definitions, so that people and agents use the same figures, including in text-to-SQL.
• Define governance rules and access rights.
• Build knowledge pipelines for RAG: indexing, chunking, metadata, permissions.
• Prepare context usable by agents: metadata, definitions, lineage, and permissions.

Profile sought

The essentials:

1. You write SQL with ease and model data for analysis.
2. Planned, tested, and monitored data pipelines are part of your track record.
3. Alongside business teams, you define metrics and ensure that the data truly means what everyone believes it to convey.
4. Data quality, documentation, and access rights matter to you.
5. Coding agents are already part of your daily life, and you verify what they produce.

A plus, not a prerequisite:

• Python for data processing.
• A cloud data platform, such as BigQuery, Snowflake, or Databricks.
• A semantic layer or a metrics store.
• Preparing documents for RAG: chunking, indexing, metadata.
• Data catalog or lineage tools.

No need to tick all the boxes to apply: if you have the core essentials and the desire to learn the rest, let's talk.

Why join us?

In a field where two dashboards sometimes display two different figures, this role consists of restoring trust: a correct figure, a shared definition, an identifiable source. This work, discreet when successful, conditions everything that other archetypes build on top.

We are AI makers: AI is built with our clients, not just for them. Their challenges become ours, and our technical choices are explained in the language of the business. The positions we take are clear; they evolve in the face of facts, never under pressure.

Our field changes every month, and this pace suits us: new technologies and new sectors are learned quickly, and habits that no longer serve are abandoned without regret. Faced with a difficult problem, the instinct is to break it down into verifiable steps, with a high level of requirement for both code and deliverables.

When something is missing, for a client or for the chapter, we build it. Progression comes through constructive feedback, knowledge sharing, asking for help without delay, and recognizing the work of others. There is much to learn, and much to build.

A counselor accompanies you during your first months. Technical onboarding opens the path, followed by a first client project; if none is ready, internal starter kits take over.

The rest is learned on projects, with AI Engineers and the support of the Context & Analytics Engineer community, particularly context engineering, which is the work that makes data usable by AI agents. From 2027 onwards, the Context & Analytics Engineer archetype will have its own skills framework and training path, in addition to the common foundation for all AI Applied Engineers (AI evaluation, production responsibility).

Later, a transverse role becomes possible (Project Tech Lead, Pre-sales Engineer, Engineering Manager), as do the AI Architect and AI Product Manager chapters.

Recruitment process

The process takes approximately four hours, spread over six stages, with only one on-site.

1. HR Interview (45 min, remote): background, motivations, and practical points, such as timeline and salary expectations.
2. Call with the CTO (15 to 30 min, remote).
3. Technical Screening (30 min, remote, with a member of the AI Applied Engineer chapter): detailed review of your past projects, followed by technical and solution design questions.
4. Code review and live coding (60 min, on-site, with a chapter member): review of an existing code repository and correction of its defects, then construction of a new feature with a coding agent and presentation of the result.
5. Technical Case Study (45 min, remote, with a chapter member): framing a business problem, proposing a technical solution, describing the evaluation method, and then discussing your choices.
6. Final Interview (30 min, remote, with a member of the department's management, Engineering Manager or Director): review of open points, selection of the archetype and level best suited to your profile, and answers to all your questions.

Depending on the stage, all AI tools are allowed, or none. During live coding, the way of working with AI assistance is observed.

Compensation: €53,000 to €63,000 gross annual salary (fixed) + up to €5,000 variable depending on experience and seniority

At Artefact, we are convinced that diversity of backgrounds, experiences, and perspectives enriches our teams. We are committed to providing an inclusive environment and equitable opportunities, where everyone can grow and express their full potential. Our recruitments are based on skills, potential, and fit for the role.