AI Engineer – European Portfolio

Role Overview

• Build AI pre-screening for incoming R&D tickets — flag vague requirements, missing acceptance criteria, and ambiguous descriptions before developer assignment; root cause of downstream rework
• Automate ticket quantification and code impact analysis — surface affected code areas and generate initial requirement breakdowns
• Automate the dev lifecycle upstream: requirements validation, ticket quality gates, and spec generation
• Implement automated CI/CD failure analysis — root cause identification, proposed fixes, and validated resolutions
• Run automated dependency vulnerability scans and implement validated fixes
• Deploy OWASP Top 10 automated scanning with proposed and validated security fixes
• Build log analysis (SIEM/CloudTrail) with smart anomaly alerting beyond what standard tooling provides
• Automate client security audit questionnaire completion from internal knowledge bases — with mandatory R&D review before any submission
• Build and maintain AI-powered product features: LLM integrations, RAG systems, intelligent automation, and custom AI agents
• Evaluate and integrate LLM providers based on cost, quality, and latency
• Establish lightweight tooling governance — new tools can be challenged and validated, not unilaterally adopted
• Build AI-assisted log file collection, parsing, and pre-analysis to accelerate ticket resolution and reduce manual investigation time
• Automate CI/CD deployment pipelines and build error scraping and real-time KPI reporting pipelines
• Build internal ticket knowledge systems from historical data — pre-classification, pre-routing, and automated resolution infrastructure
• Consolidate product documentation; auto-suggest documentation updates when code changes
• Build and maintain production AI pipelines — model serving, evaluation, monitoring, and shared infrastructure
• Handle complex escalations from Automation Specialists — workflows requiring custom code or deep integration

Requirements

• Strong software engineering in Python and/or TypeScript — clean, tested, production-ready code
• Hands-on experience building and deploying LLM-based applications in production
• RAG architecture, prompt engineering, and AI evaluation frameworks
• API design, microservices, and CI/CD pipelines (GitHub Actions, GitLab CI)
• Security engineering awareness — OWASP, dependency scanning, and SIEM tooling are a strong advantage
• Collaborative — works with engineering teams, not as an isolated AI function

Nice to Have

• MLOps/LLMOps: model serving, evaluation, monitoring, and versioning
• Vector databases (Pinecone, Weaviate, Qdrant, pgvector)
• Infrastructure-as-code, container orchestration, multi-model architectures
• Experience with enterprise SIEM tooling (Wazuh, CloudTrail, or equivalent

Tech Stack

• Microservices
• Python
• TypeScript