Jobs by Fastorial
Back to all jobs

AI Agent Architect

0 views
BybitAbu DhabiHybrid

10+ years

Posted 8 days ago

  • Docker
  • Go
  • Kafka
  • Kubernetes
  • Llm
  • Microservices
  • Node.js
  • RabbitMQ

About Us

Established in 2018, Bybit is one of the world's leading cryptocurrency exchanges and digital financial platforms, serving over 80 million users across more than 200 countries and regions. Powered by world-class technology and a user-first mindset, Bybit delivers a seamless ecosystem across trading, payments, wealth management, custody, institutional services, and Web3 - connecting users to the future of digital finance.

Our core values define how we build. We listen, care and improve to create products and experiences that put users first. Backed by a global team of ambitious builders, problem-solvers, and innovators, we foster a high-performance and fast-moving environment where talent is empowered to drive real impact at the global scale. Supported by 24/7 multilingual customer service and a strong commitment to innovation, we are shaping the future of finance through technology, collaboration, and bold execution.

Today, Bybit is recognized as one of the most trusted and transparent platforms in the digital asset industry, continuing to expand its global presence while building the infrastructure for the next generation of financial services.

About the Role

We're at an inflection point where AI is fundamentally reshaping financial infrastructure. As an AI Agent Architect, you will be a core builder of AI's intelligent ecosystem - not just writing code, but defining how next-generation financial-grade Agents perceive market signals, plan execution paths, retain business context, and orchestrate across systems. You will lead the construction of Agent capabilities purpose-built for real financial scenarios: trading intelligence, risk assessment, compliance monitoring, and smart user services - engineered to operate autonomously in crypto finance's high-velocity, high-stakes, and high-compliance environment. This is a role with genuine technical ownership. You'll make architectural decisions that directly shape the experience of hundreds of millions of users, alongside an elite engineering team with exceptional depth in LLM and Agent technology.

Key Responsibilities

  • Agent Architecture Design: Lead the architectural design of AI's intelligent Agent layer - defining agent execution models, lifecycle management, and resource isolation strategies on the Openclaw platform. Build the foundational Agent capabilities powering core financial scenarios including trading intelligence, risk assessment, and compliance monitoring, engineered for high-concurrency, low-latency, and regulatory-grade reliability.
  • Financial Scenario Agent Engineering: Translate complex financial use cases - trading signal analysis, risk identification, regulatory compliance, and intelligent customer service - into production-ready Agent workflows. Design task planning pipelines (ReAct / Plan-and-Solve / Reflection) and memory architectures (short-term, long-term, semantic memory) to ensure agents operate with precision and predictability in high-stakes environments.
  • Openclaw Platform Development & Evolution: Contribute deeply to the architectural evolution and performance optimization of Openclaw Agent Runtime. Architect plugin ecosystems, capability registries, and multi-agent collaboration frameworks to expand agent reasoning boundaries, operational toolsets, and execution flexibility.
  • Tool Ecosystem & Internal System Integration: Build a standardized tool-calling framework bridging Bybit's core trading engines, risk engines, data platforms, and external APIs. Implement rigorous tool permission controls, execution tracing, and fault-recovery mechanisms to guarantee safe, reliable, and auditable tool execution.
  • Production Quality & Observability: Lead the observability stack for Agent systems, including distributed tracing, evaluation frameworks, cost governance, and latency optimization. Establish evaluation benchmarks and guardrail frameworks tailored for financial scenarios to prevent hallucinations, guard against prompt injection, and protect sensitive financial data.
  • Technical Vision & Team Enablement: Track and internalize cutting-edge Agent research, translating breakthroughs into production AI engineering practices. Establish team-wide Agent development standards and best practices, elevating the engineering bar through code reviews, architectural RFCs, and technical mentorship.

Requirements

  • Proven LLM / Agent Engineering Experience: 3+ years of AI systems development experience, including 1+ year of production experience with LLMs, RAG systems, or Agent frameworks.
  • Hands-on Openclaw Experience: Direct development and optimization experience with Openclaw (Agent Runtime architecture, plugin ecosystem, multi-agent orchestration).
  • Systems Architecture Proficiency: Strong distributed systems design skills including microservices, message queues (Kafka / RabbitMQ), and asynchronous task scheduling.
  • Programming Expertise: Proficiency in at least one backend language (Golang / Java / Node.js), REST API design, and containerized deployment (Docker / Kubernetes).
  • Deep LLM Technical Understanding: Strong grasp of Transformer architecture, Attention mechanisms, and advanced Prompt Engineering (CoT, Few-shot, Structured Output).
  • Model Integration Experience: Production experience with leading model APIs (OpenAI, Anthropic Claude, Google Gemini) and local model inference runtimes (Ollama, vLLM).
  • Engineering Quality Standards: Strong software design fundamentals (design patterns, unit testing, CI/CD).
  • Evaluation & Tracing: Hands-on experience building LLM evaluation frameworks or Agent tracing pipelines (LangSmith / Phoenix / Langfuse).

Nice to Have

  • Experience combining MCTS, A*, or Reinforcement Learning (RL) with LLMs for planning and reasoning; familiarity with SFT / RLHF training pipelines.
  • Proven Agent system deployments in high-complexity vertical domains such as Finance, Web3, or Regulatory Compliance.
  • Open-source contributions or publications in NeurIPS / ICML / ACL / ICLR on Agent, RAG, or LLM topics.
  • Experience with multimodal Agent development, including vision-language understanding and unstructured document parsing (PDFs, financial reports, research papers).
  • Familiarity with MCP (Model Context Protocol) or prior involvement in designing and implementing Agent communication standards.

Why Join Us

  • Study Growth Fund: We support your professional development and continuous learning.
  • Internal Events: Participate in regular team-building activities, workshops, and events designed to promote collaboration and innovation.
  • Global Collaboration: Be part of a diverse, international team, working alongside colleagues from around the world.
  • Career Advancement: Access opportunities for growth and advancement within a rapidly expanding global company.
  • Internal Mobility: Grow with us - Your long-term development is important to us. We offer internal job opportunities to help build your career path.