Professional Overview
I'm a Senior AI Engineer who ships production LLM systems, not demos. I help companies turn document-heavy workflows into pipelines that survive real traffic: multi-agent checks, structured extraction with schema validation, evaluation, and cost control per document. Python, FastAPI, cloud workflows, serverless.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Own the production LLM plane for trade and finance document verification
- Custom multi-agent catalog: completeness, dates, Incoterms, HS codes, math
- Structured extract: JSON-mode LLM to Pydantic schemas, then QA autofix
- Serverless edge: FastAPI, API Gateway, JWT, YDB, queues with DLQ, retries
- Human-in-the-loop: agents draft, only an operator can approve and send
Key Achievements / KPIs
- Migrated 5-service LLM verification plane to serverless, public API unchanged
- Built 11-agent document QA catalog with routing per document type
- Prompt-as-code in git with CI drift gate; 5 models shadow-tested offline
- Shipped real-time fraud scoring (SageMaker/Lambda) with shadow + A/B rollout
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Real-time fraud scoring path on SageMaker + Lambda with SNS/SQS routing
- Shadow predictions and A/B rollout so untested models never hit customers
- FastAPI and serverless APIs on AWS and GCP; HMAC webhooks, quotas, billing
- Data plane: ~25 Airflow DAGs, Spark on Kubernetes, dbt, BigQuery
- Quality gates, pipeline tests and Slack alerts on data and model failures
Key Achievements / KPIs
- Built ~25 Airflow DAGs with quality gates for the analytics data plane
- Shipped real-time scoring with shadow + A/B; no untested model saw traffic
- 3.5 years of production ML for US enterprise Shopify merchants
AI Expertise
Skills
Employment Type
Key Achievements / KPIs
- Owned architecture decisions defended directly to business leadership
- Delivered ERP and reporting rollouts accepted by HQ and local ops
- 19 years running IT and process systems in finance and operations
Areas of Expertise
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
NLP & Prompt Engineering
Build natural language processing systems, fine-tune large language models, and craft reliable production prompts for AI-powered products.
