As a Senior Backend Engineer on our companys AI Framework team, you will build the foundational platform that enables the entire organization to design, evaluate, deploy, and operate AI agents at scale. This is a new, high-impact team responsible for creating the frameworks, tools, and guardrails that power our companys agentic ecosystem.
Youll work deeply in the agentic space, designing systems for orchestration, evaluation, observability, and safety. The platforms you build will be used by multiple teams across our company, making your impact immediate and company-wide.
Youll Own:
Agentic Framework Architecture: Designing and building our internal agentic framework, leveraging and integrating industry-standard tools such as LangChain, LangSmith, ADK, and similar ecosystems.
Evaluation and Quality Systems: Building evaluation frameworks and workflows for AI agents, including offline and online evaluations, quality metrics, regression detection, and experimentation infrastructure.
Observability, Monitoring, and Guardrails: Providing the organization with robust observability capabilities for AI agents, including tracing, logging, monitoring, cost tracking, and safety guardrails to ensure reliable and responsible usage.
Developer Enablement Platforms: Creating APIs, SDKs, and abstractions that enable product teams to easily build, test, and operate agents while adhering to platform standards.
Cross-Language Integrations: Designing integrations and tooling across Python and Java to enable seamless adoption of the AI framework within our broader backend ecosystem.
Agent Runtime and Execution Engine: Building the runtime responsible for orchestrating agent execution, managing tool calls, maintaining state and memory, and ensuring reliable execution across distributed systems.
Youll Solve:
Agent Lifecycle and Orchestration Complexity: Managing agent execution, tool usage, memory, workflows, and failure modes in production-grade systems.
AI System Reliability at Scale: Ensuring agents remain observable, debuggable, and safe as usage scales across teams and products.
Evaluation and Drift Challenges: Detecting quality regressions, model behavior changes, and unintended agent behaviors through robust evaluation and monitoring systems.
Platform Adoption Friction: Balancing flexibility with guardrails so teams can innovate quickly without compromising reliability, security, or cost controls.
Youll Impact:
Company-Wide AI Enablement: Empowering every engineering team to build agent-based solutions faster, with higher quality and confidence.
Foundational AI Infrastructure: Establishing the core frameworks, evaluations, and observability standards that all AI agents at our company will rely on.
AI Safety and Quality Bar: Raising the bar for how AI systems are evaluated, monitored, and governed across the compan
Youll work deeply in the agentic space, designing systems for orchestration, evaluation, observability, and safety. The platforms you build will be used by multiple teams across our company, making your impact immediate and company-wide.
Youll Own:
Agentic Framework Architecture: Designing and building our internal agentic framework, leveraging and integrating industry-standard tools such as LangChain, LangSmith, ADK, and similar ecosystems.
Evaluation and Quality Systems: Building evaluation frameworks and workflows for AI agents, including offline and online evaluations, quality metrics, regression detection, and experimentation infrastructure.
Observability, Monitoring, and Guardrails: Providing the organization with robust observability capabilities for AI agents, including tracing, logging, monitoring, cost tracking, and safety guardrails to ensure reliable and responsible usage.
Developer Enablement Platforms: Creating APIs, SDKs, and abstractions that enable product teams to easily build, test, and operate agents while adhering to platform standards.
Cross-Language Integrations: Designing integrations and tooling across Python and Java to enable seamless adoption of the AI framework within our broader backend ecosystem.
Agent Runtime and Execution Engine: Building the runtime responsible for orchestrating agent execution, managing tool calls, maintaining state and memory, and ensuring reliable execution across distributed systems.
Youll Solve:
Agent Lifecycle and Orchestration Complexity: Managing agent execution, tool usage, memory, workflows, and failure modes in production-grade systems.
AI System Reliability at Scale: Ensuring agents remain observable, debuggable, and safe as usage scales across teams and products.
Evaluation and Drift Challenges: Detecting quality regressions, model behavior changes, and unintended agent behaviors through robust evaluation and monitoring systems.
Platform Adoption Friction: Balancing flexibility with guardrails so teams can innovate quickly without compromising reliability, security, or cost controls.
Youll Impact:
Company-Wide AI Enablement: Empowering every engineering team to build agent-based solutions faster, with higher quality and confidence.
Foundational AI Infrastructure: Establishing the core frameworks, evaluations, and observability standards that all AI agents at our company will rely on.
AI Safety and Quality Bar: Raising the bar for how AI systems are evaluated, monitored, and governed across the compan
דרישות:
7+ years of backend engineering experience, with strong system design and platform-building expertise.
Strong analytical and problem-solving skills, with the ability to debug and resolve complex technical issues efficiently.
Hands-on experience designing and building agentic systems or agent frameworks in production, including orchestration, tool usage, memory management, and multi-step workflows.
Experience extending or building frameworks on top of tools like LangChain, LangGraph, ADK, or similar agent orchestration frameworks.
Experience designing, implementing, and operating production-grade AI agents, including handling failure modes, retries, observability, and real user traffic.
Strong understanding of AI evaluation methodologies, including agent evaluations, prompt evaluation, regression testing, and quality monitoring.
High proficiency in Python for building production-grade AI frameworks and services.
Familiarity with Java and experience integrating backend platforms or tooling into Java-based systems.
Experience building observability, monitoring, or platform tooling for distributed s המשרה מיועדת לנשים ולגברים כאחד.
7+ years of backend engineering experience, with strong system design and platform-building expertise.
Strong analytical and problem-solving skills, with the ability to debug and resolve complex technical issues efficiently.
Hands-on experience designing and building agentic systems or agent frameworks in production, including orchestration, tool usage, memory management, and multi-step workflows.
Experience extending or building frameworks on top of tools like LangChain, LangGraph, ADK, or similar agent orchestration frameworks.
Experience designing, implementing, and operating production-grade AI agents, including handling failure modes, retries, observability, and real user traffic.
Strong understanding of AI evaluation methodologies, including agent evaluations, prompt evaluation, regression testing, and quality monitoring.
High proficiency in Python for building production-grade AI frameworks and services.
Familiarity with Java and experience integrating backend platforms or tooling into Java-based systems.
Experience building observability, monitoring, or platform tooling for distributed s המשרה מיועדת לנשים ולגברים כאחד.
