AI Engineer H/F

Skaleet; Boulogne-Billancourt; Hybride; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

Remote work policy

25 days vacation

Alan Blue health insurance

Swile meal card

Office Boulogne-Billancourt

Entrepreneurial culture

Résumé du poste

Skaleet is seeking an AI/ML Engineer to join its new AI Team in Boulogne-Billancourt. You will build and own AI products, including banking agents operating in natural language and AI-powered automations across back-office processes.

You will ship production-ready AI in banking environments, focusing on reliability, scalability, and compliance, while collaborating with data engineers and product teams to continuously improve the platform.

Qualifications

• Minimum 5 years of software engineering experience, with hands-on production LLM-based agent systems.
• Strong Python backend skills: REST APIs, async, automated testing.
• Concrete experience with tool calling, RAG, agent context/memory management, and LLM quality evaluation.
• Fluency in French and English, both written and spoken.
• Master's degree in Computer Science, Machine Learning, AI, Engineering, or equivalent hands-on experience.

Responsabilités

• Build and ship Skaleet's AI products end to end, from prototypes to production deployment.
• Own the technical architecture of the agentic platform and integrate the latest advances in foundation models, agent frameworks and AI engineering.
• Design reliable agentic workflows combining LLMs, tools, banking data and human oversight.
• Define how agents reason, retrieve context, call tools, handle failures and collaborate to complete complex banking operations.
• Own AI quality, observability and evaluation, using traces, user feedback, annotated datasets, LLM-as-judge, calibration against human labels and regression gates.
• Build the integration layer between agents and Skaleet's platform: MCP servers and APIs, production-grade authentication, permission management, error handling, retries, idempotency and structured outputs.
• Develop the context and retrieval systems powering our agents: embeddings, vector search, hybrid retrieval, reranking and knowledge ingestion over Skaleet's product documentation and clients' business processes.
• Work closely with data engineers to make banking data usable by AI systems: data models, pipelines, interfaces, tenant isolation.
• Implement safeguards required for banking use cases: human validation gates, permission scoping, tenant isolation, audit trails, explainability, safe failure modes.
• Prototype quickly, iterate with banking operators, identify high-value use cases and improve the product based on real operational feedback.
• Evaluate and integrate the best available AI models and technologies based on quality, latency, cost, security and regulatory constraints.

Connaissances

Python backend

LLM agent systems

Tool calling & RAG

Observability & tracing

Guardrails

French & English

Formation

Master's degree in CS/ML

Outils

APIs (MCP)

LLM frameworks

Vector search

Description du poste

[SKALEET]

Skaleet is a fast-growing tech scale-up specializing in Core Banking, helping financial institutions in 15 countries innovate, scale, and deliver superior banking experiences. Our mission: free European banks and fintechs from legacy core banking systems, so they can finally deliver modern, modular, real-time banking experiences, without compromising on compliance or robustness.

Our ambition for the next five years: become the platform of choice for European financial institutions to modernize their infrastructure, scale their operations, and rapidly launch new banking services.

[Job Description]

Context

Skaleet just created its AI Team, with one clear ambition: enhance the banking operations of our clients through AI. Running a bank means thousands of daily back-office operations, our goal is to make these operations faster, more reliable, and more scalable.

As an AI / ML Engineer, you'll join the AI Team and report directly to Thomas LINCK, VP Plateform. You'll build and own Skaleet's AI products, a suite of specialized banking agents letting back-office operators understand, analyze, and act on the platform in natural language, plus AI-powered automations that take over recurring operational processes end to end.

You'll ship AI into production banking environments, where "mostly right" isn't an acceptable bar.

Your future missions

Architecture & delivery

• Build and ship Skaleet's AI products end to end, from early prototypes to production deployment

• Own the technical architecture of our agentic platform and continuously improve it by integrating the latest advances in foundation models, agent frameworks and AI engineering

Agents & reliability

• Design reliable agentic workflows combining LLMs, tools, banking data and human oversight

• Define how agents reason, retrieve context, call tools, handle failures and collaborate to complete complex banking operations

• Own AI quality, observability and evaluation, using traces, user feedback, annotated datasets, LLM-as-judge, calibration against human labels and regression gates

Integration & data

• Build the integration layer between agents and Skaleet's platform: MCP servers and APIs, production-grade authentication, permission management, error handling, retries, idempotency and structured outputs

• Develop the context and retrieval systems powering our agents: embeddings, vector search, hybrid retrieval, reranking and knowledge ingestion over Skaleet's product documentation and clients' business processes

• Work closely with data engineers to make banking data usable by AI systems: data models, pipelines, interfaces, tenant isolation

Security & compliance

• Implement the safeguards required for banking use cases: human validation gates, permission scoping, tenant isolation, audit trails, explainability, safe failure modes

Product & iteration

• Prototype quickly, iterate with banking operators, identify high-value use cases and improve the product based on real operational feedback

• Evaluate and integrate the best available AI models and technologies based on quality, latency, cost, security and regulatory constraints

This role is about building systems on top of existing foundation models, not training models from scratch.

[Desired Profile]

You are a great match if :

Must-have

• Minimum 5 years of software engineering experience, including significant hands-on experience building LLM-based agent systems in production

• Strong Python backend skills: REST APIs, async, automated testing

• Concrete experience with tool calling, RAG, agent context/memory management, and LLM quality evaluation

• Comfortable designing and integrating complex, data-intensive production systems

• Experience monitoring and optimizing LLM systems in production: observability, tracing, cost and latency control at scale

• Working knowledge of guardrails and defenses against prompt injection

• Fluency in French and English, both written and spoken

• Master's degree in Computer Science, Machine Learning, AI, Engineering, or equivalent hands-on experience.

Bonus points

• Strong team player with product sensitivity — you can push back on a spec that's technically unrealistic, without waiting to be asked

• Proactive, autonomous, entrepreneurial mindset, thrives on scale-up energy

• Experience in a regulated environment (banking, insurance, healthcare) where audit trail and human control are hard constraints — a plus, not a prerequisite

The benefits of joining Skaleet

• Remote Policy: Work from home 2 days per week, offering you flexibility and balance.

• 25 days of paid vacation and 12 additional days off (RTT) per year.

• The perfect health insurance: Alan Blue

• Lunch Matters: We provide a Swile card to cover your meals on workdays

• An entrepreneurial mindset and strong team spirit

• Beautiful, brand-new offices located in Boulogne-Billancourt, right next to Metro Line 10.

[Recruitment Process]

• A first video call with Maxime from the HR team to get to know each other and tell you more about Skaleet, our company culture & values (30').

• A second video call with Louis to introduce you to Skaleet’s AI product vision, the project’s ambitions, and the role you could play (30’).

• A live coding interview to assess (60').

• A final meeting at our offices in Boulogne with Victor, our Chief of Staff (60').

We look forward to discovering your profile !