AI / ML Engineer
Irsyad Zulfikar
AI Engineer shipping computer vision, LLM, and MLOps systems—from training pipelines to monitored inference on GKE and GCP.
- 3+
- years in AI
- 6
- model ensemble
- 10k+
- samples benchmarked
Experience
Production AI systems
ENB Mobile Care
AI Engineer
March 2025 – Present
Architected a production smartphone-grading pipeline of six detection, classification, and segmentation models. Led the migration from Docker Swarm to GKE, tuned per-service autoscaling, built Vertex AI training pipelines with MLflow, and added inference monitoring with VictoriaMetrics and Grafana. Benchmarked 10,000+ samples across multiple YOLO generations and shipped real-time OCR for paperless trading-machine transactions.
Lawencon Internasional
AI Engineer
April 2024 – December 2024
Built an LLM-powered CV parsing and scoring pipeline with LlamaIndex and Groq, reducing manual screening time by 50%. Developed RAG assistants with Flask and MongoDB, a live coding assessment platform, and recruitment analytics pipelines for HR teams.
Indonesia AI
Junior AI Engineer
August 2023 – February 2024
Developed vehicle detection and counting models with 86% validation accuracy and a waste-classification CNN with 82% precision on hazardous objects. Defined annotation and preprocessing standards to improve generalization across varied data conditions.
Selected work
Projects

LeafSentry AI
Bean-leaf triage that abstains instead of guessing: image-quality gating, selective prediction with calibrated abstention, a FastAPI service, and a reproducible evaluation report. Apache-2.0. 96.875% top-1 on 128 pinned upstream test images — model-level evidence, not field performance.

Axiom Alpha
Equity-analysis platform with multi-factor scoring, backtesting, market heatmaps, and screening for US and Indonesian stocks. Built the Django backend, frontend, and cloud deployment.

KenalinIkan
Indonesian fish encyclopedia for markets and kitchens: regional-name search across the archipelago, 50 species pages, 50 recipes, a 21-province season map, and a yield/cost calculator for HoReCa. Built with Next.js, PostgreSQL, a PWA shell, and a read-only public JSON API.

Crossed-Eye Detection
Computer vision pre-screening system for strabismus using facial landmarks and deep-learning classification to flag misaligned gaze axes.
YOLOv11 Detection API
Dockerized FastAPI service for YOLOv11 inference, annotated-image output, and static result delivery.

Cityscapes UNet Segmentation
UNet implementation trained on Cityscapes with resize augmentation, reaching a 0.912 Dice coefficient.
Core toolkit
Skills
core
Daily drivers across every project on this page.
ai / ml
PyTorch and ONNX ship inside LeafSentry; YOLO ran in the production smartphone-grading pipeline.
backend
FastAPI serves LeafSentry's public inference API; Django powers Axiom Alpha end to end.
mlops & cloud
Docker and Prometheus metrics keep LeafSentry's live deployment observable; GKE and Vertex AI from production grading work.
data
PostgreSQL backs Axiom Alpha and KenalinIkan in production.
Education
Telkom University
Bachelor of Computer Science
2019 – 2023
GPA: 3.8 / 4.0
Selected credentials
Building Systems with the ChatGPT API
DeepLearning.AI
Prompt Engineering with Llama 2 & 3
DeepLearning.AI
Supervised Machine Learning: Regression and Classification
DeepLearning.AI / Coursera
Full Stack Data Science Academy
Indonesia AI
Building an AI team?
I am open to AI engineering, machine learning, and computer vision opportunities.
Prefer to browse first? See what I am working on now · Run my production model
Lighthouse (mobile, November 2026): Accessibility 100 · Best Practices 100 · SEO 100.