Software Engineer – Agentic AI & Reliability Platform

About the role

We are looking for an experienced Software Engineer specialized in Agentic AI to build a centralized reliability command center. The role blends backend development, AI agents, and developer‑facing tools to deliver scalable, intelligent solutions that improve system health visibility and incident response.

Key responsibilities

• Design and implement a unified reliability command center for system health, risk, and reliability monitoring.
• Develop AI agents that assist with incident triage, root‑cause analysis, log summarization, and recommendation of next actions.
• Create developer‑facing APIs and features to enhance debugging, observability, and decision‑making.
• Leverage AI‑assisted development tools to prototype, refactor, and deliver high‑quality code efficiently.
• Own projects end‑to‑end, from requirements gathering through design, testing, rollout, and iteration.
• Collaborate with Product, Infrastructure, Data, and SRE teams to translate complex challenges into simple, scalable solutions.

Required profile

• 5+ years of backend or full‑stack engineering experience.
• Proven ability to build and operate complex production systems.
• Strong product mindset with the capacity to turn ambiguous requirements into working solutions.
• Experience owning projects from design through production rollout.
• Excellent collaboration skills across cross‑functional teams.

Required skills

• Python
• Architecting data‑intensive applications and robust APIs
• AI‑assisted development tools (Cursor, Claude, GitHub Copilot)
• Practical experience with LLMs or AI frameworks

What we offer

• Remote work flexibility
• Prepaid Medical Insurance
• Rewards Program for technology, restaurants, and more
• Learning Academy for continuous professional development
• Long‑term engagement with stability and impact