Principal Member of Technical Staff (PMTS) / Staff Software Engineer – AI Platform (Agentic Systems)

What You’ll Be Doing & Why It Matters

We are building the autonomous “software factory” that powers Slack’s global engineering organization.

As a Principal Member of Technical Staff (PMTS) / Staff Software Engineer on the Agentic Operations team, you will set the technical direction and architecture for how Slack builds, registers, and safely operates autonomous agentic systems.

You will lead cross-team initiatives to transform high-volume software engineering workflows—from multi-repo code generation to automated incident remediation—into dependable, supervised, and continuously improving agentic pipelines at enterprise scale.

The Agentic Operations team builds and operates the platforms and internal “software factories” that automate how Slack’s engineering organization develops, operates, and maintains its services. Our mission is to turn repetitive, high-volume engineering toil into reliable, supervised autonomous workflows so engineers can focus on architecture and judgment.

We design and operate the systems that power:

• Autonomous Code Generation & Remediation: Agent-driven pipelines that open, review, test, and land changes at scale across large codebases.
• Operational & Incident Automation: Agents that assist with real-time incident response, post-incident remediation, and routine production maintenance.
• Continuous Evaluation, Guardrails & Safety: Deterministic evaluation harnesses, regression test suites, and observability platforms that make non-deterministic agentic systems trustworthy in production.
• Durable Execution & State Management: Robust execution engines featuring state persistence, function-calling hooks, human-in-the-loop (HITL) approval gates, and automated rollback mechanisms.
• Continuous Data Hygiene: Agentic loops that keep Slack’s service catalog and entity metadata current and verified.

Our systems build on Slack’s agentic development platform (Speck), our Compute Platform (EKS, EC2), and the Service catalog. We define the patterns, guardrails, and operational standards that engineering teams across Slack adopt to safely run their own autonomous agents.

Core Responsibilities & Scope

• Set Technical Strategy & Architecture: Architect Slack’s agentic operations platform, defining the standards for building, registering, and operating autonomous agents and software factories safely at scale.
• Build End-to-End Autonomous Pipelines: Design autonomous pipelines (code generation, bug fixing, incident remediation) equipped with orchestration, tool integrations, and human-in-the-loop controls needed to run unattended but accountably.
• Establish Production AI Rigor: Build evaluation suites, regression harnesses, guardrails, and observability frameworks that make non-deterministic agentic systems measurable, debuggable, and safe.
• Define Ownership & Accountability Models: Establish how failures in autonomous systems are detected, attributed, and remediated, including on-call policies and operational guardrails.
• Drive Cross-Functional Adoption: Partner with platform teams (Speck, Incident Management, Deploy Safety) and consuming engineering groups to integrate agentic workflows into daily developer routines.
• Cost & Compute Governance: Advocate for cost-conscious, efficient model and compute utilization, balancing model intelligence and latency against token budgets and compute spend.
• Raise the Engineering Bar: Mentor senior engineers, drive deep architectural reviews, and author clear system designs that establish reusable technical patterns across the organization.

Minimum Requirements

• 10+ Years of Software Engineering Experience: Proven track record designing and delivering complex distributed systems at scale, with Staff/Principal-level technical judgment and organizational influence.
• Production Agentic Systems Experience: Hands-on experience building and shipping LLM-powered agents and multi-agent systems, including orchestration, structured tool/function calling, retrieval (RAG), and context window engineering.
• Production AI Rigor & Evals: Concrete experience making non-deterministic AI systems production-ready through deterministic evaluation suites, regression harnesses, guardrails, and LLM telemetry.
• Strong Distributed Systems & Backend Foundations: High engineering rigor in writing clean, scalable, maintainable code. Experience operating backend and distributed systems with direct accountability for uptime, latency, and reliability.
• Systems-Level Automation Mindset: Pragmatic approach to developer platforms and automation, comfortable operating with ambiguity and balancing rapid AI capability against production safety.
• Experience building autonomous code-generation pipelines, automated refactoring systems, or “software factories” that open PRs and land changes across monolithic or multi-repo architectures.
• Experience designing agent evaluation frameworks, prompt/context management layers, or LLM observability platforms used by other engineering teams.

Preferred Qualifications

• Deep background in service orchestration, or automated incident remediation at scale.
• Hands-on experience with AWS, Kubernetes (EKS), and Infrastructure as Code (Terraform) using reusable, maintainable abstractions.
• Active contributions to open-source agentic frameworks, developer tools, or the broader AI developer ecosystem.
• Familiarity with modern frontier model APIs and agentic frameworks (Anthropic Claude Tool Use, OpenAI function calling, Model Context Protocol/MCP, LangGraph, etc.) and a practical understanding of their failure modes.