KỸ NĂNG
- AI Engineer
MÔ TẢ CÔNG VIỆC
- Design the technical architecture for an AI-powered voice and browser-agent pipeline.
- Build and deploy production-ready AI workflows using Python and modern LLM tooling.
- Develop the voice agent conversation flow for issue classification, troubleshooting, escalation, and appointment confirmation.
- Implement RAG workflows for installation manuals, error codes, troubleshooting instructions, and internal knowledge bases.
- Design a robust retrieval strategy using embeddings, vector search, metadata filtering, chunking, reranking, and evaluation.
- Build workflow orchestration using LangChain and n8n.
- Integrate the solution with Supabase for database management, authentication, APIs, vector search, storage, and application data.
- Build or integrate a browser agent using Hyperbrowser to navigate the existing ERP/CRM interface and create appointments.
- Design safeguards for browser automation, including validation, retries, fallback handling, and auditability.
- Develop evaluation frameworks for AI responses, retrieval quality, tool usage, task completion, and conversation outcomes.
- Set up A/B testing, feature flags, prompt/version management, monitoring, and production experimentation.
- Implement observability using LangWatch and error tracking through Sentry.
- Ensure the system is modular, maintainable, testable, secure, and production-ready.
- Collaborate with Product, Engineering, and client stakeholders to clarify workflows, define success criteria, and communicate technical trade-offs.
- Support deployment and maintenance through GitHub and Vercel.
Time: CET time - VNT: 1PM - 10PM
- Build and deploy production-ready AI workflows using Python and modern LLM tooling.
- Develop the voice agent conversation flow for issue classification, troubleshooting, escalation, and appointment confirmation.
- Implement RAG workflows for installation manuals, error codes, troubleshooting instructions, and internal knowledge bases.
- Design a robust retrieval strategy using embeddings, vector search, metadata filtering, chunking, reranking, and evaluation.
- Build workflow orchestration using LangChain and n8n.
- Integrate the solution with Supabase for database management, authentication, APIs, vector search, storage, and application data.
- Build or integrate a browser agent using Hyperbrowser to navigate the existing ERP/CRM interface and create appointments.
- Design safeguards for browser automation, including validation, retries, fallback handling, and auditability.
- Develop evaluation frameworks for AI responses, retrieval quality, tool usage, task completion, and conversation outcomes.
- Set up A/B testing, feature flags, prompt/version management, monitoring, and production experimentation.
- Implement observability using LangWatch and error tracking through Sentry.
- Ensure the system is modular, maintainable, testable, secure, and production-ready.
- Collaborate with Product, Engineering, and client stakeholders to clarify workflows, define success criteria, and communicate technical trade-offs.
- Support deployment and maintenance through GitHub and Vercel.
Time: CET time - VNT: 1PM - 10PM
YÊU CẦU CÔNG VIỆC
- Fluent English (C1/C2 level) – Able to communicate complex technical concepts smoothly with international clients
- Has 4+ years of experience in applied AI/ML with production deployments
- Strong programming skills in Python (TypeScript a plus)
- Hands-on experience with LangChain and workflow orchestration (n8n)
- Familiarity with Supabase (DB, APIs, auth, vector search, storage)
- Experience with feature-flag systems (LaunchDarkly or similar)
- Comfortable building evaluation frameworks, A/B tests, and monitoring systems
- Strong knowledge of embeddings, vector DBs, and RAG workflows
- Solid engineering practices: modular, testable, maintainable code
- Has 4+ years of experience in applied AI/ML with production deployments
- Strong programming skills in Python (TypeScript a plus)
- Hands-on experience with LangChain and workflow orchestration (n8n)
- Familiarity with Supabase (DB, APIs, auth, vector search, storage)
- Experience with feature-flag systems (LaunchDarkly or similar)
- Comfortable building evaluation frameworks, A/B tests, and monitoring systems
- Strong knowledge of embeddings, vector DBs, and RAG workflows
- Solid engineering practices: modular, testable, maintainable code
QUYỀN LỢI
- Receive 100% salary from the onboarding date.
- Participate in company activities: teambuilding, travel, vacation and other activities.
- Work with large and advanced systems, have the opportunity to develop comprehensive technology skills with complex problems, requiring high accuracy.
- Participate in company activities: teambuilding, travel, vacation and other activities.
- Work with large and advanced systems, have the opportunity to develop comprehensive technology skills with complex problems, requiring high accuracy.
MỨC LƯƠNG
up to 26 triệu
work
Loại hình làm việc :
Remote
event
Hạn ứng tuyển:
18/07/2026
date_range
Kinh nghiệm:
4 năm
school
Học vấn:
Không yêu cầu
people
Số lượng:
1
switch_account
Cấp bậc:
Middle
Hỗ trợ ứng tuyển
email
quynhttd@hatonet.com