Senior AI platform and Distribution Systems Engineer
Il y a 6 heures
Meknes, Fez-Meknes, Maroc
FactTrace
Temps partiel
Gratuit avec email ou Google
Enregistrez cette offre et organisez votre recherche
Créez un compte gratuit pour enregistrer des offres d'emploi, créer des alertes et revenir à cette liste depuis votre tableau de bord.
Gratuit avec email ou Google
En continuant, vous acceptez nos Conditions d’utilisation & Politique de confidentialité.
Company Description At FactTrace, our mission is built on a simple yet critical standard: "Truth You Can Verify. AI You Can Trust."
We build next-generation enterprise verification platforms and intelligent agentic systems engineered to bring transparency, rigorous auditing, and provable reliability to generative AI and enterprise data pipelines. Operating across the UK and our growing engineering hub in Meknès, Morocco, our distributed team combines deep systems engineering with bleeding-edge AI to ensure critical digital information remains verifiable, accurate, and secure at scale.
About the Role
We are seeking a Senior AI Platform & Distributed Systems Engineer to spearhead the architecture and delivery of our next-generation enterprise intelligence platform. In this role, you will bridge the gap between high-scale, fault-tolerant backend infrastructure and modern applied AI workflows. While this position is currently an Individual Contributor (IC) role, we are specifically looking for candidates with a strong interest in stepping into a Team Lead/Technical Management position in the future as our engineering organization grows.
Key Responsibilities
Architect Distributed Microservices: Design, benchmark, and deploy low-latency, event-driven pipelines (Node.js, Python) capable of ingesting millions of files reliably under SLA-driven production targets (99.9%+ uptime). Deploy Production AI & Agentic Runtimes: Implement deterministic multi-backend LLM workflows, self-hosted Model Context Protocol (MCP) servers, RAG knowledge bases, structured tool-calling, and schema-validated fail-safes/guardrails. Infrastructure & Incident Ownership: Maintain cloud environments (AWS, Linux, VPS, Docker) and CI/CD pipelines. Implement integrated centralized logging and observability tools (such as Grafana and Prometheus), taking full ownership of root-cause analysis and operational excellence. Technical Leadership & Mentorship: Act as a senior technical authority on the team today, setting standards for code reviews and architectures, with the willingness to transition into managing and guiding engineering teams in the future. Qualifications & Technical Depth Core
Requirements:
Education:
State Engineering Degree (Diplôme d'Ingénieur d'État) in Computer Science or Software Engineering from EMI, or an equivalent elite state engineering school is preferred.
Experience:
8+ years of hands-on software engineering experience building and scaling enterprise platforms in production environments. Backend & Systems: Deep mastery of Node.js / TypeScript and Python, along with REST APIs, WebSockets, and event-driven microservices architecture. Applied AI & LLMs: Proven experience with LLM orchestration (Claude, OpenAI, local models), agentic runtimes, structured I/O tool calling, RAG pipelines, and strict safety guardrails. Databases & DevOps: Advanced competence in PostgreSQL (schema design and optimization), NoSQL (Couchbase/MongoDB), Docker, Git, and CI/CD pipelines. Familiarity with industry-standard observability tools such as Grafana and Prometheus. Languages & Working Model: English proficiency is a must-have, as is a willingness to work full-time on-site at our Meknès tech hub. Nice-to-Have / Differentiators: Direct contribution to or implementation of Model Context Protocol (MCP) clients/servers. Track record of building production RAG systems with reranking pipelines and semantic routing. Previous experience mentoring junior engineers or acting as a de facto tech lead. Reporting Line: Chief Technology Officer
Location:
Meknès Tech Hub (Full-time on-site) Department: Core Platform Engineering Contract: 6-Month Fixed-Term (CDD) leading directly to a Permanent Contract (CDI) based on delivery milestones (As we stand up our core AI platform at the Meknès Tech Hub, this initial 6-month cycle is structured to establish baseline architecture and technical ownership, paving the immediate pathway into a permanent CDI and future engineering management role).
About the Role
We are seeking a Senior AI Platform & Distributed Systems Engineer to spearhead the architecture and delivery of our next-generation enterprise intelligence platform. In this role, you will bridge the gap between high-scale, fault-tolerant backend infrastructure and modern applied AI workflows. While this position is currently an Individual Contributor (IC) role, we are specifically looking for candidates with a strong interest in stepping into a Team Lead/Technical Management position in the future as our engineering organization grows.
Key Responsibilities
Architect Distributed Microservices: Design, benchmark, and deploy low-latency, event-driven pipelines (Node.js, Python) capable of ingesting millions of files reliably under SLA-driven production targets (99.9%+ uptime). Deploy Production AI & Agentic Runtimes: Implement deterministic multi-backend LLM workflows, self-hosted Model Context Protocol (MCP) servers, RAG knowledge bases, structured tool-calling, and schema-validated fail-safes/guardrails. Infrastructure & Incident Ownership: Maintain cloud environments (AWS, Linux, VPS, Docker) and CI/CD pipelines. Implement integrated centralized logging and observability tools (such as Grafana and Prometheus), taking full ownership of root-cause analysis and operational excellence. Technical Leadership & Mentorship: Act as a senior technical authority on the team today, setting standards for code reviews and architectures, with the willingness to transition into managing and guiding engineering teams in the future. Qualifications & Technical Depth Core
Requirements:
Education:
State Engineering Degree (Diplôme d'Ingénieur d'État) in Computer Science or Software Engineering from EMI, or an equivalent elite state engineering school is preferred.
Experience:
8+ years of hands-on software engineering experience building and scaling enterprise platforms in production environments. Backend & Systems: Deep mastery of Node.js / TypeScript and Python, along with REST APIs, WebSockets, and event-driven microservices architecture. Applied AI & LLMs: Proven experience with LLM orchestration (Claude, OpenAI, local models), agentic runtimes, structured I/O tool calling, RAG pipelines, and strict safety guardrails. Databases & DevOps: Advanced competence in PostgreSQL (schema design and optimization), NoSQL (Couchbase/MongoDB), Docker, Git, and CI/CD pipelines. Familiarity with industry-standard observability tools such as Grafana and Prometheus. Languages & Working Model: English proficiency is a must-have, as is a willingness to work full-time on-site at our Meknès tech hub. Nice-to-Have / Differentiators: Direct contribution to or implementation of Model Context Protocol (MCP) clients/servers. Track record of building production RAG systems with reranking pipelines and semantic routing. Previous experience mentoring junior engineers or acting as a de facto tech lead. Reporting Line: Chief Technology Officer
Location:
Meknès Tech Hub (Full-time on-site) Department: Core Platform Engineering Contract: 6-Month Fixed-Term (CDD) leading directly to a Permanent Contract (CDI) based on delivery milestones (As we stand up our core AI platform at the Meknès Tech Hub, this initial 6-month cycle is structured to establish baseline architecture and technical ownership, paving the immediate pathway into a permanent CDI and future engineering management role).