Founding Engineer (Engineer Lead/CTO)

JAC Recruitment; Jakarta Pusat; On-site; IDR 200.000.000 - 300.000.000; Full time

Job summary

A stealth startup in Indonesia is seeking a Founding Engineer to build LLM-powered customer support automation. This role requires hands-on experience with LLMs and API integration. Candidates must possess a strong background in Python development and be ready to transition from a sole contributor to a technical leader role as the company scales. Opportunities for growth to CTO are available.

Qualifications

• Proven track record building and shipping LLM-powered applications end-to-end.
• Expertise with RAG pipelines, LangChain or LlamaIndex, and vector databases.
• Strong Python development skills, including FastAPI, PyTorch/TensorFlow.

Responsibilities

• Develop the intelligence layer using LLMs for e-commerce customer support.
• Implement RAG pipelines, vector search, and conversational flows.
• Connect AI workflows with e-commerce APIs and messaging platforms.

Skills

LLM-powered applications

RAG pipelines

Python development

API integration

Problem-solving

Education

CS/adjacent degree or equivalent coding expertise

Tools

FastAPI

PyTorch

TensorFlow

Hugging Face

vector databases

Job description

Overview

Our client is a new stealth startup in Indonesia that are currently looking for a Founding Engineer with hands-on GenAI builder experience to ship LLM-powered customer support automation (RAG + LangChain + WhatsApp/Shopee APIs) from scratch.

Their mission is to give businesses their time back. Our client is building an AI-powered co-pilot that integrates with WhatsApp to automate time-consuming tasks for small and medium-sized businesses in Indonesia and Southeast Asia. Furthermore, their vision is to be the default AI support agent for every WhatsApp-powered business in emerging markets, starting with e-commerce brands.

Key Requirements

• Proven track record building and shipping LLM-powered applications end-to-end (not just research/POCs).
• Expertise with RAG pipelines, LangChain or LlamaIndex, and vector databases (Pinecone, Weaviate, FAISS, Milvus).
• Strong Python development (FastAPI, PyTorch/TensorFlow, Hugging Face).
• Experience integrating LLMs into production systems (chatbots, copilots, customer-facing workflows).
• Familiarity with 3rd-party APIs (WhatsApp, TikTok, Shopee, Shopify, Zendesk).
• Comfortable with 0→1 building in early-stage environments; able to balance speed with scalability.
• CS/adjacent degree or equivalent coding expertise; strong problem-solving and debugging skills.
• Stability in past roles; clear evidence of recent hands-on builds.
• Willing to start hands-on coding full-time, with a path to CTO as the company scales (hiring/managing engineers, shaping tech vision).

Key Responsibilities

Design & Build the AI Core

Develop the intelligence layer using LLMs (OpenAI, Anthropic, Gemini, etc.) for e-commerce customer support workflows (order tracking, refunds, cancellations, shipping status).

End-to-End Automation Engine

Implement RAG pipelines, vector search, and conversational flows.

Build automation that can independently query APIs (Shopee/TikTok/WhatsApp) and execute actions like refunds, order updates, etc.

Integrate with Commerce Platforms

Connect AI workflows with e-commerce APIs (example: Shopee, Tokopedia, TikTok Shop) and messaging platforms (WhatsApp Business).

Build the User Experience for Sellers

• Monitor AI conversations.
• Intervene when needed.
• Manage customer interactions in one place.

Product Iteration & Feedback Loops

Deploy MVP with first e-commerce pilot users.

Collect data & feedback to refine conversational accuracy, workflow automation, and user trust.

Technical Leadership

Define the AI technical vision & architecture.

Own decisions on LLM frameworks, vector DBs, orchestration tools.

Establish coding standards, infra setup, and security.

Future Scaling

Transition from sole contributor to team leader / CTO.

Recruit, mentor, and lead engineering hires as the company scales.