Remote AI Agent Engineer
Hạn nộp hồ sơ: 20/10/2026 (Còn 29 ngày)
Ứng tuyển sớm để được ưu tiên
Kết nối với Nhà tuyển dụng để tìm hiểu thông tin và gia tăng cơ hội trúng tuyển
Nhà tuyển dụng đang online
Mô tả công việc
Tóm tắt công việc
The core product experience runs on an LLM-driven agent that extracts data from client-submitted receipts and documents over WhatsApp, proposes accounting entries, and answers staff questions inside the web app. We're hiring an AI/Agent Engineer to take ownership of this entire layer, making it cheaper, safer and more reliable while closing specific security gaps (prompt injection, unchecked tool authorization) identified in a recent technical audit. You will work alongside a backend-leaning Fullstack Engineer, who owns the surrounding application and infrastructure.
Responsibilities
Own the LLM integration layer used for document extraction (OCR), accounting-entry proposals, and the in-app chat agent, currently built on Anthropic/OpenAI APIs
Implement prompt caching to cut redundant token usage. An identified -83% cost-reduction opportunity and introduce per-tenant usage budgets and quotas
Harden the agent against prompt injection: treat all extracted document text as untrusted input, and require explicit confirmation gates before any tool call that grants data access, creates a contact, or moves money
Replace the agent's currently hard-coded (effectively disabled) permission model with real, enforced per-tool authorization checks
Evaluate and implement model tiering, cheaper models for extraction, stronger models for judgment calls and plan a fallback provider for resilience
Build an evaluation/golden-file test harness so model or prompt changes can be validated before shipping to production
Implement PII redaction before data is sent to third-party LLM providers, and partner with the Fullstack Engineer to log every agent tool call to an audit trail
Advise on data-processing-agreement and data-residency questions for the AI sub-processors (Anthropic, OpenAI), alongside the company's data-protection advisor
Contribute to the n8n-side automation where it touches AI extraction, the document-intake pipeline and coordinating handoffs with the Fullstack Engineer.
You'll love working here!
Competitive salary package.
Mon-Fri, flexible remote working.
12 days of annual leave and 3 additional special holidays (Swedish National Day, Christmas Eve & your Birthday).
Annual leave increases with loyalty.
Premium health care package for employees & family members.
English, professional working environment.
Opportunities to gain hands-on experience in cutting-edge technologies.
The core product experience runs on an LLM-driven agent that extracts data from client-submitted receipts and documents over WhatsApp, proposes accounting entries, and answers staff questions inside the web app. We're hiring an AI/Agent Engineer to take ownership of this entire layer, making it cheaper, safer and more reliable while closing specific security gaps (prompt injection, unchecked tool authorization) identified in a recent technical audit. You will work alongside a backend-leaning Fullstack Engineer, who owns the surrounding application and infrastructure.
Responsibilities
Own the LLM integration layer used for document extraction (OCR), accounting-entry proposals, and the in-app chat agent, currently built on Anthropic/OpenAI APIs
Implement prompt caching to cut redundant token usage. An identified -83% cost-reduction opportunity and introduce per-tenant usage budgets and quotas
Harden the agent against prompt injection: treat all extracted document text as untrusted input, and require explicit confirmation gates before any tool call that grants data access, creates a contact, or moves money
Replace the agent's currently hard-coded (effectively disabled) permission model with real, enforced per-tool authorization checks
Evaluate and implement model tiering, cheaper models for extraction, stronger models for judgment calls and plan a fallback provider for resilience
Build an evaluation/golden-file test harness so model or prompt changes can be validated before shipping to production
Implement PII redaction before data is sent to third-party LLM providers, and partner with the Fullstack Engineer to log every agent tool call to an audit trail
Advise on data-processing-agreement and data-residency questions for the AI sub-processors (Anthropic, OpenAI), alongside the company's data-protection advisor
Contribute to the n8n-side automation where it touches AI extraction, the document-intake pipeline and coordinating handoffs with the Fullstack Engineer.
You'll love working here!
Competitive salary package.
Mon-Fri, flexible remote working.
12 days of annual leave and 3 additional special holidays (Swedish National Day, Christmas Eve & your Birthday).
Annual leave increases with loyalty.
Premium health care package for employees & family members.
English, professional working environment.
Opportunities to gain hands-on experience in cutting-edge technologies.
Yêu cầu
3+ years of experience building production applications on top of LLM APIs (Anthropic Claude, OpenAI, or equivalent)
Hands-on experience with agentic tool-use patterns, function/tool calling, multi-step agent loops, not just single-shot prompting
Strong prompt-engineering skills, including context management and techniques for defending against prompt injection
Proficiency in Python or TypeScript, sufficient to build and modify a backend AI-integration layer
Experience building or using evaluation frameworks/golden-file testing for LLM-based systems
Practical understanding of LLM cost structures and optimisation techniques, prompt caching, context trimming, model tiering
Working knowledge of security concerns specific to LLM systems: prompt injection, data exfiltration via generated content, unsafe tool authorization
Clear written communication in English; able to work asynchronously across time zones
Hands-on experience with agentic tool-use patterns, function/tool calling, multi-step agent loops, not just single-shot prompting
Strong prompt-engineering skills, including context management and techniques for defending against prompt injection
Proficiency in Python or TypeScript, sufficient to build and modify a backend AI-integration layer
Experience building or using evaluation frameworks/golden-file testing for LLM-based systems
Practical understanding of LLM cost structures and optimisation techniques, prompt caching, context trimming, model tiering
Working knowledge of security concerns specific to LLM systems: prompt injection, data exfiltration via generated content, unsafe tool authorization
Clear written communication in English; able to work asynchronously across time zones
Thông tin khác
Python
AI (Artificial Intelligence)
Machine Learning
API
TypeScript
OpenAI
Caching
LLM
Claude
AI (Artificial Intelligence)
Machine Learning
API
TypeScript
OpenAI
Caching
LLM
Claude
Thông tin chung
- Thu nhập: Thỏa Thuận
Nơi làm việc
- Floor 20, TNR Tower, 180-192 Nguyen Cong Tru Street, Ben Thanh, Ho Chi Minh
Việc làm tương tự khác
EL4 - Software Studio
Hồ Chí Minh
range VND 75,000,000
Công ty Bảo Hiểm Nhân Thọ Dai-ichi Việt Nam - Văn Phòng Cầu Giấy
Hồ Chí Minh
You'll love it
Công Ty TNHH Money Forward Việt Nam
Hà Nội, Hồ Chí Minh
You'll love it
CÔNG TY CỔ PHẦN TRUSTING SOCIAL - AI Fintech Trusting Social
Hồ Chí Minh
Thỏa Thuận
Công ty TNHH R Techno Việt Nam
Hồ Chí Minh
Từ 40tr /tháng
TỔNG CÔNG TY DỊCH VỤ VIỄN THÔNG (VNPT VINAPHONE)
Hà Nội, Hồ Chí Minh
Thu nhập từ 800 tr
Fram^ - Swedish-Vietnamese IT Company
Xem trang công ty- Địa chỉ công ty: Rox Tower, quận 1, HCM
- Quy mô: Từ 101 - 500 nhân viên
Thông tin công việc
Vị trí:
Nhân viên
Hình thức làm việc:
Toàn thời gian; Làm tại nhà
Việc làm tương tự
Cảnh báo dấu hiệu lừa đảo tuyển dụng
Đội ngũ hỗ trợ của JobOKO sẵn sàng đồng hành, tư vấn và giới thiệu những cơ hội việc làm phù hợp, giúp Ứng viên tự tin phát triển sự nghiệp và chinh phục mục tiêu nghề nghiệp bền vững.
Hotline CSKH
1900.63.63.84
Công ty Cổ phần JobOKO Toàn cầu
Đội ngũ hỗ trợ của JobOKO luôn chủ động tư vấn các giải pháp tuyển dụng tối ưu, cam kết đồng hành và hỗ trợ Quý Nhà tuyển dụng đạt được hiệu quả tuyển dụng bền vững.
Hotline CSKH
0962.107.888
Công ty Cổ phần JobOKO Toàn cầu