5 days ago
Kuala Lumpur, MalaysiaStaff+
Responsibilities
- Design and implement the AI agent SDK, orchestration engine, runtime, and core primitives.
- Expand the MCP ecosystem by wrapping internal systems as MCP servers, sub-agents, and agent skills, with tool discovery, registration, RBAC, rate limiting, and version management.
- Build the agent development lifecycle from specification and evaluation through implementation, testing, A/B testing, canary releases, monitoring, and iteration.
- Own agent effectiveness, accuracy, resolution rate, cost, latency, and personalization optimization through data feedback.
- Develop production-grade multi-agent systems and continuously iterate after 0-to-1 launch.
Requirements
- Bachelor's degree or above in computer science, software engineering, or a related field.
- P7 candidates require 6+ years of experience, including 3+ years in AI or agent development; P7+ candidates require 8+ years and 0-to-1 agent platform experience.
- Proficiency in Go or Python and ability to produce production-grade system designs and TRD documentation.
- Deep expertise in LLM APIs, prompt engineering, ReAct patterns, and context-window management, including token budgeting, history compression, and sub-agent compression.
- Production experience launching and continuously iterating an AI agent system beyond demo or proof-of-concept work.
- Experience with at least one orchestration framework, such as LangGraph, Dify, Eino, Embabel, or OpenAI Agents SDK.
- Hands-on experience with multi-agent collaboration, including agent teams, parallel execution, DAGs, or handoffs.
- Deep expertise in either RAG engineering, including vector retrieval, hybrid search, and reranking, or evaluation systems, including LLM-as-Judge, golden sets, regression testing, and A/B testing.
- Ability to quantify effectiveness and cost, optimize token usage, understand PII desensitization and prompt-injection protection, and identify compliance boundaries in financial scenarios.
- Preferred qualifications include experience building agent simulation or benchmarking platforms, private LLM deployment, relevant domain expertise, AI security research, open-source contributions, and public technical influence through blogs, talks, papers, or open-source projects.
Benefits
- Study Growth Fund for professional development and continuous learning.
- Regular internal team-building activities, workshops, and events.
- Opportunity to collaborate globally with an international team.
- Career advancement opportunities within a rapidly expanding company.
- Internal mobility opportunities to support long-term career development.
Categories
