AI Integration Specialist

📋 Role Overview

Responsible for designing and integrating production LLM solutions (OpenAI, Anthropic Claude, DeepSeek, HuggingFace) into client web products and 20byte internal AI workflows.

🎯 Key Deliverables & Responsibilities

• Integrate LLM APIs (OpenAI, Anthropic, Gemini, Ollama) into existing web application backends.
• Build autonomous AI agents using LangChain, LlamaIndex, or CrewAI frameworks.
• Develop production RAG (Retrieval-Augmented Generation) pipelines with Vector Databases (Pinecone, Qdrant, ChromaDB).
• Evaluate AI model performance, latency, token consumption, and cost optimization.
• Collaborate with engineering teams to ensure data privacy, security compliance, and robust error fallback handling.

🎓 Qualifications & Requirements

• Indonesian citizen residing in Indonesia (100% Full Remote position).
• 2+ years of hands-on software development experience with AI / LLMs / Vector Databases.
• Professional English proficiency (written & spoken) for seamless interaction with global client teams.
• Proficient in Python or TypeScript / Node.js.
• Solid understanding of REST APIs, Webhooks, and asynchronous workflows.
• Passionate about generative AI, multi-agent architectures, and continuous AI evaluation.

✨ Preferred Qualifications (Nice-to-Have)

• Experience fine-tuning open-source models (Llama 3, Mistral)
• Deployment on Cloudflare Workers or AWS Lambda