Software Development Engineer – AI Observability Platform

About the role

We are an early‑stage AI startup building an AI‑driven observability platform that works alongside SRE, DevOps, and Cloud Operations teams. As a Software Development Engineer you will help design and implement the core platform and intelligent AI agents that automate incident investigation and remediation.

Key responsibilities

• Design and develop a scalable observability platform for cloud‑native and hybrid infrastructures.
• Create AI agents that analyze logs, traces, and metrics in real time and provide automated insights.
• Build fault‑tolerant frameworks for AI agents and large‑scale analytics pipelines.
• Engineer resilient distributed systems with high reliability and performance.
• Implement and fine‑tune large language models for natural‑language querying and automated troubleshooting.

Required profile

• 5+ years of experience building highly scalable distributed systems and analytics pipelines.
• Bachelor’s degree in Computer Science, Engineering or related field (Master’s/PhD a plus).
• Proven track record of delivering production‑grade cloud infrastructure solutions.

Required skills

• Strong programming in Python and Golang (Rust a plus).
• Hands‑on experience with cloud platforms (AWS, GCP, Azure) and Kubernetes.
• Deep knowledge of observability tools such as Prometheus, OpenTelemetry, Grafana, Elastic.
• Familiarity with LLMs, AI agent frameworks (e.g., LangChain, Autogen).
• Experience with stream‑processing frameworks and real‑time data pipelines.
• Proficiency with SQL, NoSQL, ClickHouse and time‑series databases.