Ahmad Saladin

Remote AI/ML Engineer for production AI systems

I help teams build LLM/RAG apps, computer vision pipelines, FastAPI model APIs, vector search systems, n8n automations, and cloud inference backends.

Based in Indonesia, UTC+7. Available for APAC/Europe overlap and async global teams.

Open to remote roles, contractor work, freelance projects, part-time engagements, and project-based AI/backend implementation.

What I Build

LLM/RAG Applications

Document assistants, retrieval pipelines, vector search, tool-calling workflows, structured data collection, and AI app backends. Built for enterprise clients in healthcare and business automation.

PythonFastAPIQdrantLangGraphRAGTool Calling

Computer Vision Systems

Image processing, segmentation, detection, OpenCV/PyTorch pipelines, sliding-window inference, post-processing, and production inference APIs. Deployed to both cloud APIs and mobile devices (TorchScript + JNI).

PyTorchOpenCVONNXSegmentationDetectionSliding-Window Inference

AI Backend & Model Serving

FastAPI/Flask model APIs, async job queues, Redis/RabbitMQ workers, object storage flows, callback/webhook patterns, and cloud deployment. Serving real-time healthcare workflows and long-running inference jobs.

FastAPIFlaskRedisRabbitMQDockerAWSGCPS3/GCS

n8n + AI Automation

Workflow automations combining APIs, LLMs, webhooks, human approval, messaging integrations, and business process automation. Built for business process automation with LLM integration.

n8nWebhooksLLMsGmailTelegramPostgresAutomation

Featured Case Studies

View all case studies

LLM/RAG Assistant with Tool Calling

Case study

AI assistant workflow with retrieval, tool calling, structured information collection, and backend integration.

LLMRAGQdrantFastAPILangGraphTool Calling

Computer Vision Segmentation Pipeline

Case study

Production-oriented image segmentation workflow with preprocessing, sliding-window inference, post-processing, API/mobile deployment considerations, and visualization outputs.

Computer VisionPyTorchOpenCVSegmentationONNXAPI Deployment

Async AI Inference Backend

Case study

Backend architecture for long-running AI jobs using API endpoints, queue workers, object storage, status tracking, and callback/webhook delivery.

FastAPIFlaskRedisRabbitMQDockerAWSGCPS3/GCS

Available for roles and project work

I am available for remote AI/ML engineering roles, contractor engagements, freelance PoCs, part-time implementation support, and project-based AI/backend work.

For Hiring Teams

Looking for an AI/ML engineer who can build production-oriented systems, not just experiments.

  • AI/ML Engineer
  • LLM/RAG Engineer
  • Computer Vision Engineer
  • AI Backend Engineer
  • Python Backend Engineer with ML deployment experience

For Clients & Agencies

Need help building AI prototypes, backend integrations, computer vision pipelines, RAG apps, or workflow automations.

  • RAG/document assistant prototypes
  • Computer vision pipelines
  • Async model inference APIs
  • AI workflow automation
  • n8n + LLM implementation
  • Backend integration for AI products

Tech Stack

AI / ML

PyTorchscikit-learnONNXOpenCVembeddingssegmentationdetectionLangChainLlamaIndex

LLM / Agents

RAGQdrantFAISSLangGraphtool callingOpenAI APIGemini APIGPT-Realtimeprompt workflows

Backend

PythonFastAPIFlaskRedisRabbitMQREST APIswebhooksasync pipelines

Cloud / Infra

DockerAWSGCPS3/GCSCloudflare PagesVPS deployment

Languages

PythonJavaScript/TypeScriptSQLKotlinC/C++

Automation

n8nTelegramGmailPostgresworkflow automation

Availability

Based in Indonesia, UTC+7. Available for APAC/Europe overlap and async global teams.

Open to remote roles, contractor work, freelance projects, part-time engagements, and project-based AI/backend implementation.

Can I help you build this AI system?

Start with the case studies or reach out directly with the system you want to build.