SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Atlan is building the context layer for enterprise AI—infrastructure that helps enterprises operationalize AI safely and with business context. The company is named a Leader by Gartner and Forrester across data catalogs, governance, and metadata management.
You'll join the Reliability team, which runs a multi-agent AI SRE platform already live in production. Today, agents investigate incidents, remediate them, and resolve networking tickets across every tenant. The team is small and shipped fast; the scope has now outgrown them, and the hardest problems are wide open.
This is not an incident-command SRE seat—the philosophy is that if a human is fixing production by hand, the system has failed. You'll join a mature, opinionated codebase with documented architecture decisions and eval-gated pull requests, and make it better.
Key responsibilities:
- Make investigation agents accurate enough that engineers trust them without re-checking. Treat every wrong diagnosis as a class of failure to remove, not a one-off bug.
- Grow auto-remediation coverage safely, from a handful of playbooks to dozens, earning autonomy in stages (dry run, human-approved, autonomous).
- Own the evals that decide when an agent can be trusted. Build fault-injection benchmarks and eval harnesses; set pass marks before the run and validate the harness itself.
- Design the gates that let agents write to production: fail-closed checks, kill switches, approval flows, blast-radius limits. Start from "what happens when the agent is wrong?"
- Build new agents where toil says they belong. Each agent maps to a category of toil it removes.
- Build the platform for other teams. Clean interfaces, guardrails, safe defaults so teams beyond reliability can trust the platform on their own production.
- Ship the unglamorous fix when it matters. Stop the bleeding first, then remove the class.
What makes you a match:
- You've lived operational toil. You've carried a pager, owned incidents end to end, or worked a support/escalation queue long enough to know which pain is worth removing.
- You remove classes, not tasks. You can point to a recurring operational problem you made disappear and explain the category behind it.
- You start from the problem and measure by adoption. When you describe something you built, you reach for who used it and what changed, with real numbers and real denominators.
- AI has changed how you work structurally. You've rebuilt a core part of your own work end to end with AI so it's different, not just faster. You've shipped an AI-native workflow that other people depend on.
- You have failure-mode humility. You know what an agent being wrong on production costs. You think in false-positive rates, rollback paths, and blast radius.
- You build for someone else's production. Clean interfaces, documented failure modes, safe defaults. Experience getting other teams to adopt a platform you built helps, but the instinct matters more than track record.
- You raise the bar in an existing codebase. You can join a high-rigor system, contribute at its standard quickly, and improve it rather than rewrite it.
- You write code when code is the right tool. Deterministic code for routing, filtering, and safety before any generative step. You think in systems and use agents as leverage, not as a replacement for judgment.
- Reliability work genuinely energizes you. You see operational efficiency as mission-critical for a company whose product is trust in data and AI.
Working hours: Best with overlap between roughly 11am–8pm IST.
Not a fit if you want to design the perfect autonomous platform before shipping anything, your instinct is to make toil faster rather than make it disappear, or you're fluent in agents but have never owned the consequences of one being wrong.
