Principal AI Agent Development Engineer/Architect

Role Overview

Principal AI Agent Development Engineer/Architect at Bybit, a leading global cryptocurrency exchange and digital financial platform. This role is based in Hong Kong, Kuala Lumpur (Malaysia), or Abu Dhabi, and requires relocation to one of these locations.

Company Overview

Established in 2018, Bybit serves over 80 million users across more than 200 countries and regions. The company operates a seamless ecosystem spanning trading, payments, wealth management, custody, institutional services, and Web3. Bybit is recognized as one of the most trusted and transparent platforms in the digital asset industry, supported by world-class technology, a user-first mindset, 24/7 multilingual customer service, and a global team of ambitious builders and innovators.

Role Purpose

Design, build, and own end-to-end AI agent systems from 0-to-1 launch through continuous iteration. Lead orchestration engine development, MCP integration, agent development lifecycle toolchains, and optimization of agent effectiveness and cost across accuracy, resolution rate, latency, and personalization.

Key Responsibilities

Agent SDK & Runtime

• Design and implement the orchestration engine, runtime, and core primitives for agent systems.
• Ensure the agentic loop is both steerable and verifiable while remaining conversational and adaptive.

MCP Integration & Tool Management

• Wrap internal systems as MCP servers, sub-agents, and agent skills.
• Unify tool discovery, dynamic registration, role-based access control (RBAC), rate limiting, and version management.

Agent Development Lifecycle

• Build toolchains adapted to the non-deterministic behavior of agents.
• Cover the full loop: Specification → Evaluation → Build → Test → A/B Testing → Canary Deployment → Monitoring → Iteration.

Effectiveness & Cost Ownership

• Own accuracy, resolution rate, cost, and latency metrics.
• Build agent personalization optimization loops through data feedback.

Qualifications & Experience

• Bachelor's degree or above in Computer Science, Software Engineering, or related field.
• Minimum 6+ years of engineering experience with 3+ years focused on AI/Agent systems.
• Candidates with 8+ years of experience and hands-on 0-to-1 agent platform delivery are strongly preferred.
• Production-grade agent experience: full 0-to-1 launch with continuous iteration loop (clearly distinguished from demo or POC work).

Skills & Competencies

Programming & System Design

• Proficiency in Go or Python.
• Capable of production-grade system design and Technical Requirements Documentation (TRD) writing.

LLM Application Engineering

• Deep expertise in LLM APIs, prompt engineering, and ReAct patterns.
• Advanced knowledge of context window management including token budgeting, history compression, and sub-agent compression.

Agent Engineering Practice

• Hands-on familiarity with at least one orchestration framework: LangGraph, Dify, Eino, Embabel, or OpenAI Agents SDK.
• Hands-on experience with multi-agent collaboration including agent teams, parallel execution, DAG workflows, and agent handoff patterns.

Adjacent Agent Capabilities

• Deep expertise in at least one of the following:
• RAG engineering (vector retrieval, hybrid search, reranking).
• Evaluation systems (LLM-as-Judge, golden set benchmarking, regression testing, A/B testing).

Engineering Mindset

• Ability to quantify effectiveness and cost with token optimization thinking.
• Understanding of PII desensitization and prompt injection protection.
• Ability to identify compliance boundaries in financial scenarios.

Additional Information

Bonus Qualifications

• 0-to-1 experience building an agent simulation or benchmarking platform (τ-Bench scale).
• Private LLM deployment experience: vLLM, Triton, DeepSeek, Qwen, or GLM.
• Domain expertise in crypto AI (risk control, KYC, compliance), AIOps (alert root cause analysis, diagnostic tooling), customer service AI, or code AI.
• AI security research with published work on prompt injection, jailbreak defense, or Smart Contract AI security.
• Open-source contributions to LangChain, LangGraph, Dify, MCP, Eino, Vercel AI SDK, or similar projects.
• Public technical influence including blog posts, conference talks, papers, or prominent open-source projects.

Benefits

• Study Growth Fund supporting professional development and continuous learning.
• Internal events including team-building activities, workshops, and collaborative innovation programs.
• Global collaboration with a diverse, international team.
• Career advancement opportunities within a rapidly expanding global company.
• Internal mobility and long-term career development pathways.