Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m an applied AI engineer based in Ottawa, focused on building production-ready generative AI systems, especially RAG and agentic workflows. I enjoy turning messy, real-world enterprise content into fast, reliable AI experiences—whether it’s redesigning document ingestion with vision-LMM enrichment, implementing hybrid retrieval (dense+sparse) with deduplication, or creating robust evaluation pipelines to prove quality before deployment. I also bring strong cloud and data engineering experience across Azure, Microsoft Fabric, and Databricks, with a practical emphasis on governance, observability, and data sovereignty constraints. From deploying PII de-identification services and load-tested managed endpoints to designing routing and tool-calling agent architectures with human-gated workflows, I aim to deliver systems that are deterministic-first, measurable, and safe for regulated environments.…I’m an applied AI engineer based in Ottawa, focused on building production-ready generative AI systems, especially RAG and agentic workflows. I enjoy turning messy, real-world enterprise content into fast, reliable AI experiences—whether it’s redesigning document ingestion with vision-LMM enrichment, implementing hybrid retrieval (dense+sparse) with deduplication, or creating robust evaluation pipelines to prove quality before deployment. I also bring strong cloud and data engineering experience across Azure, Microsoft Fabric, and Databricks, with a practical emphasis on governance, observability, and data sovereignty constraints. From deploying PII de-identification services and load-tested managed endpoints to designing routing and tool-calling agent architectures with human-gated workflows, I aim to deliver systems that are deterministic-first, measurable, and safe for regulated environments.

Hadi amiri

AI Engineer, Data Engineer, AI Developer, +3





I’m an applied AI engineer based in Ottawa, focused on building production-ready generative AI systems, especially RAG and agentic workflows. I enjoy turning messy, real-world enterprise content into fast, reliable AI experiences—whether it’s redesigning document ingestion with vision-LMM enrichment, implementing hybrid retrieval (dense+sparse) with deduplication, or creating robust evaluation pipelines to prove quality before deployment. I also bring strong cloud and data engineering experience across Azure, Microsoft Fabric, and Databricks, with a practical emphasis on governance, observability, and data sovereignty constraints. From deploying PII de-identification services and load-tested managed endpoints to designing routing and tool-calling agent architectures with human-gated workflows, I aim to deliver systems that are deterministic-first, measurable, and safe for regulated environments.…I’m an applied AI engineer based in Ottawa, focused on building production-ready generative AI systems, especially RAG and agentic workflows. I enjoy turning messy, real-world enterprise content into fast, reliable AI experiences—whether it’s redesigning document ingestion with vision-LMM enrichment, implementing hybrid retrieval (dense+sparse) with deduplication, or creating robust evaluation pipelines to prove quality before deployment. I also bring strong cloud and data engineering experience across Azure, Microsoft Fabric, and Databricks, with a practical emphasis on governance, observability, and data sovereignty constraints. From deploying PII de-identification services and load-tested managed endpoints to designing routing and tool-calling agent architectures with human-gated workflows, I aim to deliver systems that are deterministic-first, measurable, and safe for regulated environments.

Available to hire

I’m an applied AI engineer based in Ottawa, focused on building production-ready generative AI systems, especially RAG and agentic workflows. I enjoy turning messy, real-world enterprise content into fast, reliable AI experiences—whether it’s redesigning document ingestion with vision-LMM enrichment, implementing hybrid retrieval (dense+sparse) with deduplication, or creating robust evaluation pipelines to prove quality before deployment.

I also bring strong cloud and data engineering experience across Azure, Microsoft Fabric, and Databricks, with a practical emphasis on governance, observability, and data sovereignty constraints. From deploying PII de-identification services and load-tested managed endpoints to designing routing and tool-calling agent architectures with human-gated workflows, I aim to deliver systems that are deterministic-first, measurable, and safe for regulated environments.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Beginner

Beginner

Beginner

Beginner

Language

English

Fluent

Persian

Fluent

French

Beginner

Work Experience

Applied AI Engineer / GenAI Engineer / Cloud Data Engineer at Revolution Data Platforms

January 1, 2024 - Present

Delivered client-facing generative AI and cloud data platforms across telecom, federal government, healthcare, and energy. Optimized an air-gapped, Kubernetes-hosted agentic PDF pipeline using vision-LLM enrichment and addressed a cross-encoder reloading bottleneck, reducing ingestion time 2.3x and RAG agent response time from 36s to 6.6s (~80%). Built hybrid dense+sparse retrieval on Qdrant with content-hash deduplication and extended ingestion to additional file formats; implemented synthetic golden datasets and RAG evaluation using Langfuse tracing. Benchmarked 11 vision LLMs for production selection and built LangGraph agent tooling with parallel validation/judge nodes and bounded auto-fix loops, keeping LLM usage deterministic-first and human-gated inside the client’s Azure AI Foundry tenant. Deployed a production PII de-identification service (Microsoft Presidio + RoBERTa NER, optional LLM layer) reaching 94.9% redaction accuracy and 0% over-redaction after diagnosing systemic

Applied AI / GenAI Engineer at Revolution Data Platforms

January 1, 2024 - Present

Built production RAG ingestion and retrieval pipelines for enterprise clients, including hybrid dense+sparse retrieval with Qdrant, vision-LLM enrichment, chunking, cross-encoder reranking, and content-hash deduplication. Implemented RAG fallback strategies leveraging Cosmos DB. Developed agentic systems using LangGraph state machines for multi-skill tool orchestration, provider-agnostic LLM clients (Anthropic, Azure OpenAI, Azure AI Foundry), MCP tool integration, and human-in-the-loop gating. Created LLM evaluation harnesses with synthetic golden datasets using RAGAS and DeepEval, and added observability via Langfuse (datasets, tracing, AgentOps) on production Kubernetes. Delivered cloud data engineering capabilities including SSIS-to-Fabric/Databricks migration automation, medallion (bronze/silver/gold) architecture, Unity Catalog and Delta Live Tables, data masking, and event-driven schema-change detection. Deployed and governed AI services on Azure ML managed endpoints with Docker

Network IT Assistant at Bell Technical Solutions

January 1, 2023 - January 1, 2024

Diagnosed and resolved telecommunications and network system issues, supporting configuration, maintenance, and upgrades for enterprise environments.

Research Assistant & Teaching Assistant at University of Ottawa

January 1, 2020 - January 1, 2023

Conducted machine learning and neural network research, including approximate Bayesian neural networks for inference-time uncertainty quantification in probabilistic classification (published at IEEE). Built a multimodal emotion and bipolar-severity assessment system using large-scale video frame datasets and combining VGG-Face visual features with audio deep belief network components and LSTM-based video classification. Supported teaching by delivering tutorials for up to 180 students on uncertainty evaluation in machine learning, computer architecture, and electrical circuits.

Research Assistant / Teaching Assistant at University of Ottawa

January 1, 2020 - January 1, 2023

Conducted research on approximate Bayesian neural networks for inference-time uncertainty quantification in probabilistic classification, improving reliability of clinical decision-making. Built a multimodal emotion and bipolar-severity assessment system using VGG-Face and FER2013 for visual features, a deep belief network for audio, early fusion, and an LSTM for video classification on datasets exceeding 2M frames. Supported teaching as a TA for courses including uncertainty evaluation in machine learning, computer architecture, and electrical circuits.

Backend & Database Developer at Tamtaam Development Company

January 1, 2016 - January 1, 2019

Designed and tuned MS SQL Server databases using normalization, indexing, and stored procedures, and automated data loading with SSIS. Built C# / ASP.NET backend services, configured REST APIs and third-party integrations such as payment gateways, and implemented role-based authentication.

Backend/ Database Developer at Tamtaam Development Company

January 1, 2016 - January 1, 2018

Built and optimized MS SQL Server databases (normalization, indexing, stored procedures) and automated ETL using SSIS. Developed C# / ASP.NET backends for web applications, configured REST APIs and third-party integrations (including payment gateways), and implemented role-based authentication with Git-based collaboration.