This role will lead the team constructing the workflows and tools for our Builders, the governed Agent Platform (Cloud Agents, per-agent and per-instance identity, the Cortex code index, SkillTree, and an MCP gateway), and production-grade agentic systems like the Self-Healing System's Triage, Fix, and Watch agents. This role will also manage and guide Forward Deployed Engineers that embed with teams across the organization to help them build software and automation in alignment with our Builder Tools guardrails. This is the team that builds the engine that fuels our goal of reimagining how Software is built in the age of AI.
Job Responsibilities:
- Own the vision and roadmap for our Builder Tools – key self-service components enabling our Engineering teams to scale their use of AI and support our AI DLC initiatives.
- Lead the design and delivery of the governed Agent Platform: Cloud Agents, per-agent identity via GitHub App (so commits are attributable to the agent rather than a person), per-instance/on-behalf-of identity for delegated user access, a Cognito-authenticated MCP gateway, the Cortex code/artifact/ticket index, SkillTree, and the Artifacts store.
- Ship and operate the Self-Healing System's production agents in sequence: Agent 1 (Triage) and Agent 2 (Fix) against the documented eligibility policy (owning layer confirmed, Cortex-indexed repo, test coverage exists, single service/module, P2 or below) and exclusion list (firmware-to-field, access control, BIPA/biometric, payment, safety-critical door/gate logic), then Agent 3 (Watch) once trust is established.
- Close cross-stack telemetry and correlation gaps — threading device_serial, trace_id/span_id, account_id, deploy_id, and session_id across Datadog, OpenTelemetry, and cloud/video/mobile APM — partnering with Forward Deployed AI Engineers on the firmware side of the gap.
- Own the engineering half of token and compute cost governance: diagnose why the heaviest users consume the most, implement regular context compaction, and route to open-source or cheaper models where they fit.
- Track and report platform-health metrics: agent-authored PRs merged, correct first-assignment rate on cross-layer defects, and mean time-to-root-cause.
- Partner with Engineering leadership on governance policy and adoption reporting, and with Forward Deployed AI Engineers on firmware- and hardware-specific platform needs surfaced from the field.
- Represent the Agent Platform and builder-pipeline roadmap in architecture reviews, planning ceremonies, and executive reporting on progress toward the autonomous-organization goal.
- Comply with health and safety guidelines and rules; managers should also ensure compliance across their teams.
- Protect Chamberlain Group’s reputation by keeping information confidential.
- Maintain professional and technical knowledge by attending educational workshops, reading professional publications, establishing personal networks, and participating in professional societies.
- Contribute to the team effort by accomplishing related results and participating on projects as needed
Job Requirements:
- Bachelor's Degree in Computer Science or engineering related field
- An advanced degree in directly applicable area of study may substitute for up to two (2) years of job related experience
- 7+ years in software or platform engineering, including 2+ years leading or managing a technical team.
- Hands-on production experience building or operating LLM/agent-based systems, not just prototypes.
Knowledge, Skills, and Abilities:
- Experience building internal developer platforms, CI/CD systems, or paved-road tooling at scale.
- Hands-on experience with agent/tool-calling architectures such as MCP (Model Context Protocol), including designing gateways, tool servers, or agent runtimes.
- Familiarity with OpenTelemetry and cross-system correlation (trace IDs, span IDs, and similar identity threading across otherwise siloed telemetry stores).
- Experience designing identity and access models for non-human actors (service identities, GitHub Apps, delegated/on-behalf-of authorization).
- Working knowledge of major cloud platforms (AWS and/or Azure) and modern CI/CD and DevOps tooling (GitHub Actions, Jenkins, or similar).
- Excellent communication skills — able to translate platform strategy into a compelling narrative for both engineers and executive stakeholders.
Preferred Job Requirements:
- Experience building or operating an internal code/knowledge index (e.g., embeddings-based code search, RAG over a codebase) at production scale.
Knowledge, Skills, and Abilities:
- Direct experience with Anthropic Claude, Claude Code, or comparable agentic coding assistants in a production developer-tooling context.
- Familiarity with IoT/connected-device telemetry (e.g., MQTT, Memfault, embedded crash reporting) a plus given Chamberlain's hardware footprint.
#LI-LN1
The pay range for this position is $129,700.00 - $226,900.00; base pay offered may vary depending on a number of factors including, but not limited to, the position offered, location, education, training, and/or experience. In addition to base pay, also offered is a comprehensive benefits package and 401k contribution (all benefits are subject to eligibility requirements). This position is eligible for participation in a short-term incentive plan subject to the terms of the applicable plans and policies.
