G
AI Engineering Team Lead
לא צויןמשרה מלאהAI EngineeringEnterprise SoftwareHR Technology
Lead and mentor an AI engineering team while remaining hands-on in developing an enterprise agentic AI platform. Own agent workflows from design and evaluation through production deployment and iteration.
תחומי אחריות
- Manage, mentor, and develop a team of AI and software engineers.
- Allocate work, plan sprints, and oversee agile team ceremonies.
- Design, build, and code multi-agent systems and orchestration, including intent routing, planning, tool use, and coordination.
- Set technical direction and make architecture decisions for scalable LLM applications grounded in a knowledge graph.
- Integrate LLMs with tool-calling protocols and enterprise systems, business logic, and workflows.
- Build evaluation harnesses, guardrails, and safety and bias checks.
- Improve agent latency, cost, and reliability; take systems from prototype to production with monitoring and observability.
- Collaborate with Product, Data, and Design teams to translate customer needs into agent capabilities and prioritize roadmaps.
- Guide the team through rapid development cycles and changing priorities while maintaining delivery quality.
דרישות
- At least five years of hands-on experience as a backend, AI, or software engineer building complex, scalable distributed systems in production.
- At least two years of experience managing or leading a software or AI engineering team.
- Hands-on experience building and shipping LLM agents to production.
- Experience with at least one agent orchestration framework, such as LangGraph, LangChain, AutoGen, CrewAI, or Semantic Kernel.
- Strong Python skills and solid software engineering fundamentals.
- Agile project management experience, including sprint planning and execution.
- Ability to work effectively in a fast-paced environment with changing priorities.
- Strong communication and stakeholder collaboration skills.
יתרון
- At least two years of hands-on experience with LLMs or generative AI.
- Experience with RAG, embeddings, and vector databases.
- Experience with tool use, function calling, and external system integrations.
- Familiarity with MCP, agent memory, and planning or reasoning patterns.
- Experience with bias evaluation, guardrails, and AI governance.