AGI 全栈工程师
我们要做的,是把 AI 真正接入 IoT 世界:让摄像头能理解画面、让设备能听懂指令、让海量视频数据产生业务价值,是客户真正在用、愿意付费的产品功能。 你将: - 将视觉 AI (人形检测、包裹识别、异常行为分析)、LLM (视频摘要、指令交互)、语音 AI 集成进 Ti RTC 平台,打造有付费价值的 AI 增值服务 - 独立负责 AI 功能全链路工程化:模型/API 选型、接
加载中...
As an AI Algorithm Engineer, you will design and build the core AI systems powering Brix’s
recruiting OS—from LLM-based reasoning and agents, to matching algorithms and workflow
automation.
—Building agentic AI systems capable of planning, tool use, memory, and autonomous task
execution
—Designing multi-agent coordination and workflow orchestration
—Developing candidate–role matching, skill extraction, trait inference, and ranking algorithms —
—Improving LLM performance (prompting, fine-tuning, RAG, model routing)
—Shipping production-quality AI features with rapid iteration cycles
—Owning model quality, reliability, and performance metrics
We're looking for AI-native, builder-type engineers who thrive in ambiguity.
l Experience architecting long-context, multi-step, or persistent agents
l Knowledge of agent planning architectures (ReAct, Reflexion, Tree-of-Thought,
Graph-of-Thought, RA-As-A-Graph, AutoGen, CrewAI, Swarm)
l Ability to design robust state machines for agent behavior
l Experience with long-term memory, episodic memory, vector databases
l Memory compression / summarization strategies
l Schema design for agent state
l Experience creating eval suites (MMLU-style, behavioral tests, golden datasets)
l Familiarity with output scoring + model routing
l Human-in-the-loop feedback pipelines
Familiarity with:
l Strong backend engineering (Python, FastAPI, Node, or Go)
l Kafka / event queues / async workers
l Docker, Kubernetes, CI/CD
Nice to have:
l Familiar with AI hardware architecture design, cloud architecture, AWS certificate is a strong
plus.
l Research ability to implement new agent architectures from papers.
Critical differentiator (please highlight this)
You have built AI agents yourself—either: as a successful side project / indie project, OR as a
startup founder / technical owner who designed and implemented agent systems end-to-end
Nice to Have: Hands-on model tuning, AI system building, open-source work, startup experience,
curiosity for recruiting / org design / people systems—or willingness to rapidly learn
l Ship AI systems used by Google, TikTok, Luma, and fast-scaling startups
l Use technology to genuinely change how people work and grow
l Strong resources ($10M+ funding, $50M+ revenue trajectory )
l A small, exceptional team you help build
If you believe AI should elevate people, not replace them—and you want to build the
注册并登录后即可查看
我们要做的,是把 AI 真正接入 IoT 世界:让摄像头能理解画面、让设备能听懂指令、让海量视频数据产生业务价值,是客户真正在用、愿意付费的产品功能。 你将: - 将视觉 AI (人形检测、包裹识别、异常行为分析)、LLM (视频摘要、指令交互)、语音 AI 集成进 Ti RTC 平台,打造有付费价值的 AI 增值服务 - 独立负责 AI 功能全链路工程化:模型/API 选型、接
APP 产品 AI 化(提升交易活跃度与用户粘性) 智能交易助手: 负责开发 AI 辅助交易功能(如基于自然语言的指令下单、智能止盈止损策略建议)。 行情辅助决策: 利用大模型( LLM )集成多源信息(新闻、推特情绪、链上数据),为用户提供实时研报、代币分析及风险预警。 个性化推荐: 基于用户交易行为,利用机器学习模型进行个性化的币种推荐、策略跟单推荐及投教内容分发。 客服机
1 、负责大模型在金融支付方向的应用落地,支持达成业务以及技术的指标; 2 、负责大模型在智能营销、智能推荐、智能风控等业务领域的应用落地,降低平台运营成本、助力金融支付业务达成目标; 3 、负责大模型在智能监控、智能巡检、智能 Oncall 等技术领域的应用落地,降低平台运营成本、提升金融支付系统稳定性; 4 、负责大模型在工程领域的应用落地范式的探索,积极探索微调、
1、参与Pippit Web与App核心功能开发,负责视频和图片内容生成和编辑能力,通过调研、评估和引入前沿AI能力,优化和编排AI生成链路,协同产品、算法等团队提升营销内容的生成效果; 2、参与Pippit Agent的开发,参与Prompt 、等RAG等优化工作,MCP协议链路搭建与性能调优; 3、参与市场调研与分析,确保营销工具Web与App体验保持在业内的领先位置; 4、理