Engineer II (AI Enablement)

Kpler; Paris; Sur place; EUR 70 000 - 90 000; Plein temps

Résumé du poste

Kpler is seeking an Engineer II to join the AI Enablement crew, building tools, agents, and integrations that help every function in the company work with AI at scale.

As a strong individual contributor, you will own features end-to-end—from design through production operation—and collaborate with a senior engineer and lead to accelerate company‑wide AI adoption.

Qualifications

• 3+ years of professional engineering experience.
• Experience building and operating production systems end-to-end (services, APIs, or tooling).
• Hands-on experience building with LLMs (features, agents, automations, or serious side projects with production-quality practices).
• Understanding of system design, databases/data modelling, and application architecture.
• Familiarity with cloud infrastructure and CI/CD pipelines.
• Strong problem-solving and collaboration skills, with a user-centric mindset.
• Proficiency in Python and/or TypeScript.
• LLM application development: model APIs, prompt/context engineering, basic RAG patterns.
• API design and data integration across multiple systems and sources.
• Database design, SQL, and data modelling.
• Familiarity with cloud services (AWS preferred), containerisation (Docker/Kubernetes), and CI/CD practices.

Responsabilités

• Build, tailor, and operate AI agents and assistants for internal functions, owning features end-to-end from design through deployment and production operation (including testing and CI/CD).
• Build and maintain knowledge-base pipelines: collecting, structuring, and keeping current the content that AI systems rely on to be accurate and useful.
• Integrate AI systems with company tools and data sources through well-structured, safe APIs and connectors.
• Apply the crew's security guardrails and responsible-AI practices: access control, data privacy, and human-in-the-loop safeguards.
• Build user-facing tooling and interfaces where the work calls for it, spanning UIs and the backend services behind them.
• Instrument what you ship: adoption, quality, and cost metrics that show whether a solution is working.
• Gather feedback from internal users, identify friction points, and turn them into concrete improvements.
• Keep owned systems reliable, observable, and maintainable; participate in incident response and RCA for owned services.
• Provide context and clarity through documentation and runbooks so others understand what's built and why.
• Contribute to the crew's shared frameworks and to AI-assisted engineering practices a

Connaissances

Python

TypeScript

LLM development

CI/CD

Docker/Kubernetes

AWS

APIs

SQL/Data modelling

Outils

Docker

Kubernetes

AWS

CI/CD pipelines

Description du poste

As an Engineer II on Kpler's new AI Enablement crew, you will build the tools, agents, and integrations that help every function in the company work with AI at scale.

As a strong individual contributor, you will be responsible for the entire lifecycle of features and projects - breaking down problems, owning them from design through production operation, and coordinating with others where the work spans more than one person.

The work is varied and hands-on: building and tailoring AI agents and assistants for internal teams, curating the knowledge bases they rely on, integrating them safely with company systems, and building the interfaces and tooling around them.

You will work alongside a senior engineer and a lead who will support your growth in a fast-moving, high-visibility area of the company. To begin with, the emphasis will be on delivering Kpler's company-wide AI adoption plan; your areas of focus will shift over time with the crew's priorities

Key Responsibilities

• Build, tailor, and operate AI agents and assistants for internal functions, owning features end-to-end from design through deployment and production operation (including testing and CI/CD).
• Build and maintain knowledge-base pipelines: collecting, structuring, and keeping current the content that AI systems rely on to be accurate and useful.
• Integrate AI systems with company tools and data sources through well-structured, safe APIs and connectors.
• Apply the crew's security guardrails and responsible-AI practices: access control, data privacy, and human-in-the-loop safeguards.
• Build user-facing tooling and interfaces where the work calls for it, spanning UIs and the backend services behind them.
• Instrument what you ship: adoption, quality, and cost metrics that show whether a solution is working.
• Gather feedback from internal users, identify friction points, and turn them into concrete improvements.
• Keep owned systems reliable, observable, and maintainable; participate in incident response and RCA for owned services.
• Provide context and clarity through documentation and runbooks so others understand what's built and why.
• Contribute to the crew's shared frameworks and to AI-assisted engineering practices a

Essential Experience & Background

• 3+ years of professional engineering experience.
• Experience building and operating production systems end-to-end (services, APIs, or tooling).
• Hands-on experience building with LLMs (features, agents, automations, or serious side projects with production-quality practices).
• Understanding of system design, databases/data modelling, and application architecture.
• Familiarity with cloud infrastructure and CI/CD pipelines.
• Strong problem-solving and collaboration skills, with a user-centric mindset.
• Proficiency in Python and/or TypeScript.
• LLM application development: model APIs, prompt/context engineering, basic RAG patterns.
• API design and data integration across multiple systems and sources.
• Database design, SQL, and data modelling.
• Familiarity with cloud services (AWS preferred), containerisation (Docker/Kubernetes), and CI/CD practices.

Desirable

• Experience with agent frameworks, MCP-style tool interfaces, RAG, or knowledge-base systems.
• Experience integrating third-party SaaS APIs.
• Full-stack experience — building web UIs as well as their supporting backend services.
• Experience building internal or developer-facing tools.
• Exposure to LLM evaluation, observability, or prompt/context engineering.