ML/MLOps engineer focused on production-grade systems at the intersection of LLM security & agentic infrastructure, computer vision, and geospatial ML — with ~6 years building deep learning systems, scalable data pipelines, and cloud infrastructure (GCP/AWS). Currently at Torc Robotics on the Data Quality Assurance ML Pipeline.

I build the full stack an organization needs to run AI systems in production. Data foundations, LLM serving and GPU orchestration, and observability with incident response — end to end. I specialize in production-shaped platforms: unified serving contracts across heterogeneous backends, cost-safe GPU scheduling, contract-validated data pipelines, and evidence-grounded operational tooling. Success is measured by serving reliability, GPU cost-safety, and observability that closes the loop — not notebook demos.

Production-shaped multi-backend LLM serving and GPU-orchestration platform. One unified serving contract across vLLM, Triton Inference Server, Ray Serve, KServe, and BentoML — with real GPU infra patterns (MIG partitioning, Kueue multi-tenant scheduling, Karpenter autoscaling) validated in CI and applied out-of-band so no GPUs are burned in the pipeline. Includes SageMaker / Bedrock integration, LoRA/PEFT fine-tuning, DVC data versioning, pluggable MLflow/W&B tracking, TensorRT-LLM templates, GPTQ/AWQ/FP8 quantization, a benchmark-driven routing gateway, and a LangGraph advisor agent that is tool-grounded and non-fabricating — CI asserts every number it states is backed by Prometheus/benchmark evidence from that run.

LLM Serving · GPU Orchestration · Kueue · Karpenter · KServe · vLLM · Triton · Ray Serve · Quantization · MLOps

Vulcan's sibling platform: a unified fleet telemetry, data-quality, MLOps, and observability system currently in active architecture and early-build. Devices stream into a Kafka/Redpanda bus; Ray and Flink harden the data path; Iceberg + Dagster form the lakehouse and orchestration spine; drift-monitor, incident-engine, and OpenTelemetry close the operational loop — with an AI copilot for natural-language query/explain over platform data. Polyglot monorepo (Go for incident-engine / API gateway / CLI, Python for ingestion / drift / copilot, TypeScript for the dashboard, Terraform / Helm / ArgoCD for infra). Ambitious, well-designed scope — not yet feature-complete.

Fleet Telemetry · Iceberg · Dagster · Kafka · Ray · Flink · OpenTelemetry · MLOps · Observability

Production-validated AV telemetry lakehouse — the data/lakehouse foundation Argus grew out of. Mock fleet telemetry simulator, two-layer Pydantic + Pandera contract validation with dead-letter-queue isolation, Terraform-provisioned S3 + Glue + IAM, and PyArrow/Parquet columnar storage with Hive partitioning, deployed via Docker Compose. Verified production-run metrics: 42,972 records ingested, 91.8% acceptance rate, 0% post-gate contract rejections.

Data Contracts · Pandera · PyArrow · Parquet · Terraform · S3 · Glue · Docker Compose

• aegis — Defense-in-depth security gateway for LLM apps and agents: input/output threat detection, policy-as-code (CEL), tool/MCP permission gating with taint tracking, continuous red-teaming, Ed25519-signed tamper-evident audit trail, and drop-in SDKs.
• AegisFlow — Autonomous multi-agent incident response engine (Temporal, PydanticAI, OpenTelemetry) that triages observability alerts and plans mitigations.
• smart-assistant — Personal knowledge assistant and workflow agent.
• edgevision — Edge CV security/anomaly detection with YOLO + ByteTrack.

• terra-OBIA — Object-Based Image Analysis platform for forestry stand delineation, wetland classification, and land cover mapping at province scale.
• terra-obia-etl — ETL pipeline harmonizing GeoNB/GNB Open Data into labeled training polygons.

• NEXUS-CV — Real-time multi-modal computer vision platform with live observability and full MLOps lifecycle.
• multi-modal-od — Sensor-fusion object detection (radar, LiDAR, camera) for autonomous driving.
• sentinel-ray — Distributed camera telemetry ingestion with Ray, statistical drift detection, and automated incident orchestration.
• vanguard-telemetry-monitor — Fleet telemetry simulation and observability platform with production-like anomaly injection.
• vit-fastapi-cloud-deploy — FastAPI image classification service, evolved into a cloud-deployed Vision Transformer pipeline.
• cuda-optimization — Deep learning optimization guide adapted for Apple Metal Performance Shaders.
• See also hydra-data-factory above — the AV telemetry lakehouse foundation behind Argus.

• task-master — Production FastAPI + PostgreSQL REST API with Docker and CI/CD.
• bert-inference — Containerized DistilBERT sentiment-analysis inference service.

Production-quality platforms are resource-efficient and evidence-grounded by design — not bolted on after the model works. I treat serving contracts, GPU cost-safety, and observability as first-class systems problems: unify backends, schedule capacity without burning money in CI, validate data at the gate, and close the loop with metrics that survive contact with production. Success is measured by deployment metrics — serving reliability, GPU utilization under multi-tenant constraints, pipeline acceptance rates, and operational signal fidelity — not theoretical benchmarks that never leave the lab.

📍 Fredericton, NB, Canada · 🌐 hamidmatiny.github.io