R&d, Manager - AI Python Frameworks

Gong Gong · Enterprise · Tel Aviv, Israel · Engineering

Engineering Manager to lead a team building the foundational agentic framework, including architecture, evaluation systems, observability, guardrails, and developer enablement, for AI agents at Gong. The role involves hands-on coding, system design, and team leadership, focusing on enabling other engineering teams to build and operate AI agents safely and reliably in production.

What you'd actually do

  1. Designing and building Gong’s internal agentic framework, leveraging and integrating industry-standard tools such as LangChain, LangSmith, ADK, and similar ecosystems.
  2. Building evaluation frameworks and workflows for AI agents, including offline and online evaluations, quality metrics, regression detection, and experimentation infrastructure.
  3. Leading a squad of 3-4 senior engineers, fostering a culture of technical excellence, and managing end-to-end delivery in a fast-paced environment. You will spend approximately 50% of your time hands-on, architecting core systems and reviewing code, and 50% leading the team, mentoring engineers, and aligning with cross-functional stakeholders.
  4. 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.
  5. Creating APIs, SDKs, and abstractions that enable product teams to easily build, test, and operate agents while adhering to platform standards.

Skills

Required

  • 8+ years of backend engineering experience
  • Strong system design and platform-building expertise
  • Hands-on experience with agentic systems and frameworks such as LangChain, LangSmith, ADK, or equivalent agent orchestration platforms.
  • 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 systems.
  • Strong analytical skills and the ability to reason about complex, evolving AI-driven systems.
  • Experience with cloud platforms and scalable microservices architectures.
  • Excellent communication skills and a strong platform mindset, with experience enabling multiple teams.

Nice to have

  • Tech leadership or team leading experience is an advantage.

What the JD emphasized

  • Agentic Framework Architecture
  • Evaluation and Quality Systems
  • Observability, Monitoring, and Guardrails
  • Developer Enablement Platforms
  • Agent Lifecycle and Orchestration Complexity
  • AI System Reliability at Scale
  • Evaluation and Drift Challenges
  • Platform Adoption Friction
  • LangChain
  • LangSmith
  • ADK
  • agent orchestration platforms
  • AI evaluation methodologies
  • agent evaluations
  • prompt evaluation
  • regression testing
  • quality monitoring

Other signals

  • building agentic framework
  • evaluation systems for AI agents
  • observability and guardrails for AI agents
  • developer enablement for AI agents