The role
We're hiring an AI Engineer to design and build the LLM-powered features at the core of our product. You'll work on retrieval-augmented generation systems, agentic workflows, and the integration of language models into operational software where correctness and latency matter.
This is a hands-on engineering role. You will be responsible for taking AI features from prototype to production, and for making the design choices that determine how reliable, fast, and useful they are.
In this role, you will:
- Design and implement retrieval-augmented generation pipelines over structured and unstructured operational data.
- Build agentic workflows where language models plan, call tools, and execute multi-step operational tasks.
- Develop and maintain evaluation frameworks for LLM features in production.
- Work with the data and product teams to define the right shape of the data layer for retrieval, indexing, and grounding.
- Optimize cost, latency, and reliability of LLM features at scale.
- Contribute to the broader AI strategy of the product.
Qualifications
- At least three (4) years of software engineering experience.
- Production experience building LLM-powered features : RAG, agents, function calling, or fine-tuned models.
- Strong Python.
- Working comfort with SQL and modern data infrastructure.
- Strong written and spoken English.
- Based in or willing to relocate to Casablanca.
Nice-to-haves
- Experience with vector databases and retrieval systems at scale.
- Experience designing evaluation frameworks for LLM applications.
- Experience with agentic frameworks and tool-use patterns.
- Background in applied machine learning or NLP.
- Experience working with proprietary or domain-specific data.
- Familiarity with telecom, IoT, or industrial software.
Compensation
Competitive base salary and meaningful equity through our stock option plan.
Benefits
- Health insurance
- Equipment of your choice
- Flexible vacation
- Office in Casablanca
MLNetworks is an equal-opportunity employer.