Lead Software Engineer

Job Description

Develop agentic operations capabilities, including agent workflows, reusable lifecycle and orchestration components, monitoring, and usage metering. Track agent and model performance metrics, implement retrieval-augmented generation, and define approval gates for high-stakes actions.

Requirements: Candidates should have DevOps or site reliability engineering experience and hands-on experience with large language models, vector databases, and Model Context Protocol. They should be proficient in Python and Go, familiar with agent frameworks and retrieval-augmented generation, and have a strong background in telemetry and observability.

Key Skills: Agentic AI, LangGraph, CrewAI, AutoGen, Python, Go, Kubernetes, Terraform, Retrieval-Augmented Generation, Model Context Protocol, CI/CD, DevOps, Site Reliability Engineering, Large Language Models, Vector Databases, Telemetry and Observability