Software Development Engineer

Responsibilities:

• Design and develop a next-generation scalable observability platform for modern cloud-native and hybrid infrastructures that works in tandem with AI agents.
• Create intelligent AI agents to analyse logs, traces, and metrics in real time, delivering automated insights and remediation.
• Build scalable and fault-tolerant AI agent frameworks.
• Engineer and optimise large-scale analytics pipelines to process high-velocity telemetry data.
• Build resilient distributed systems with high reliability, performance, and fault tolerance.
• Implement and fine-tune LLMs for natural language querying and automated troubleshooting.
• Partner with ML engineers to streamline AI model deployment and management.

Requirements:

• Strong programming skills in Python and Golang (experience with Rust is a plus).
• Track record of building distributed systems and large-scale analytics pipelines.
• Hands-on experience with cloud infrastructure (AWS, GCP, or Azure) and Kubernetes.
• Deep understanding of observability technologies (Prometheus, OpenTelemetry, Grafana, Elastic, etc. )
• Knowledge of LLMs, AI agents, and agent frameworks like LangChain; AutoGen is a plus.
• Experience with stream processing and real-time data processing frameworks.
• Proficiency in database technologies (SQL and NoSQL, ClickHouse, Time-Series DBs).
• 5+ years of relevant experience in building highly scalable systems.
• Bachelor's degree in Computer Science, Engineering, or a related field (Master's/PhD is a plus).