AI Prompt Evaluator — TELUS Digital
05/2025 - 03/2026
- Evaluated LLM outputs for accuracy, safety, and instruction-following.
- Refined prompts and interaction flows to improve reliability and reduce ambiguity.
Available for new projects · Europe-based
Production AI systems
Automated precision.
AI Systems Engineer (RAG, Agents, Automation) I design and build production-ready AI systems with a focus on reliability, orchestration, and real-world constraints.
Worked on:
Compliance • Automation • Data Workflows • B2B SaaS
System snapshot
OperationalPipeline reliabilityValidation-first
Compliance posturePrivacy-aware
Delivery modelB2B production
RAG • Agents • Automation in real constraints
Experience
Independent AI Systems Engineer — Self-employed
2024 - Present
- Built production-style AI systems across RAG, document analysis, compliance workflows, and backend automation.
- Focused on deterministic pipelines, privacy-aware processing, and reliable AI-assisted outputs.
Selected work
Production systems built for reliability, compliance, and measurable business impact across European B2B contexts.
Featured project
FileGPT.dev
Architecture
RAG with tenant isolation
Reliability
Citations + guarded retrieval
Business
Faster decision velocity
Problem: Internal knowledge was spread across files and inboxes, so teams lost hours searching for answers and still doubted source reliability.
Solution: FileGPT.dev is a secure, enterprise-ready RAG platform: chat with your documents using citations, tenant-isolated storage, and cost-aware caching so API spend stays predictable.
Impact: Decision cycles became faster, onboarding improved, and leadership gained confidence that teams were acting on traceable, source-backed information.
Next.js 15SupabaseRAGVercel AI SDKGeminipgvector
TrustRespond.ai
Architecture
Document-to-Excel orchestration
Reliability
Output validation + formatting safety
Business
Deal-cycle acceleration
Problem: Enterprise B2B deals stall on massive vendor security questionnaires—often 200-row Excel files—while teams spend weeks mapping SOC 2 reports and internal policies into spreadsheets that break and lose context.
Solution: TrustRespond.ai ingests compliance documents into pgvector, reads the client's questionnaire, runs an advanced RAG pipeline with Gemini 2.5 Flash, and outputs a fully populated Excel file—without breaking the original formatting.
Impact: Typical runs finish in about 12 seconds instead of weeks—saving on the order of 40 engineering and sales hours per client and keeping deal cycles from stalling on compliance paperwork.
Next.js 15SupabasepgvectorGemini 2.5StripeTailwind CSS
ComplianceRadar
Architecture
Scan + scoring pipeline
Reliability
Policy and source grounding
Business
Lower legal risk exposure
Problem: SMBs face rising AI Act, GDPR, and ePrivacy risk but cannot justify expensive enterprise compliance programs.
Solution: ComplianceRadar delivers fast, self-serve compliance diagnosis with clear next actions and affordable upgrade paths for deeper support.
Impact: Companies move from uncertainty to action quickly, reduce legal exposure, and keep product launches on schedule.
Next.jsGemini AIPrismaStripeNextAuthVercel
Additional Projects
Additional systems and case studies available on request.
Hausheld
Impact: Teams reduced coordination overhead, improved service reliability, and gained audit-ready documentation for regulated care delivery.
Next.jsFastAPIPostgreSQLAWSPostGIS
Croatia 360
Impact: Users plan faster with less friction, discover more relevant options, and convert inspiration into completed travel decisions.
Next.jsi18nOpenAITailwind CSS
How I build systems
AI workflow architecture
A lightweight view of how I structure production-ready AI systems: deterministic flow control around LLM intelligence, with validation and observability built in.
User input
Requests enter through typed interfaces with schema-safe parsing and context capture to avoid ambiguity at the edge.
Reliability cues
Traceable steps and outputs
Validation before delivery
Policy-aware orchestration
Want a system like this for your team?
I specialize in AI-powered systems, GDPR-ready platforms, and production-grade full-stack applications for European businesses. Tell me what you're building and I'll respond within 24 hours.
Skills
Backend
PythonNode.jsFastAPISQLAlchemyPostGISAlembicPrismaPostgreSQLPydanticREST APIsJWT
AI & Data
RAGOpenAI APIGoogle GeminiPineconeVercel AI SDKEmbeddingsVector searchConversation memory
Frontend
Next.jsReactTypeScriptTailwind CSSPWAi18nFramer MotionShadcn/RadixRecharts
DevOps
DockerAWS (eu-central-1)Google CloudVercelCI/CDGit
About
I design and build production-ready AI systems focusing on agent orchestration, RAG pipelines, and real-world automation workflows.
My work centers on turning unstructured data and complex requirements into reliable systems by combining LLMs with structured logic, validation layers, and deterministic workflows. The goal is not just to generate outputs, but to ensure consistency, traceability, and control in production environments.
Recently, I have been building systems in areas like compliance, document processing, and workflow automation where AI needs to operate under real constraints such as data privacy, reliability, and regulatory requirements.
I am particularly interested in building systems where AI is only one component of a larger architecture, working alongside backend services, data pipelines, and rule-based logic to solve real-world problems.
I came to tech through a non-traditional path, which shaped how I approach engineering: understand the real workflow first, then design systems that actually hold up in practice not just in demos.
Get in touch
Have a project in mind? Send a message and I'll get back to you (usually within 24 hours).