Overview
We are looking for an experienced Senior Backend Engineer with 6-10 years of experience to build AI-based tools aimed at automating Site Reliability Engineering (SRE) Incident Management processes. The ideal candidate will have a profound understanding of using Large Language Models (LLMs) to analyze logs and events, generating actionable insights.
Key Responsibilities:
• Design, develop, and implement AI-based automation tools for SRE Incident Management.
• Good experience working with OpenAI or other LLM models with understanding of prompting, tool calling, etc.
• Utilize LLMs to analyze logs and events for generating insights and automating processes.
• Work with data parsing, chunking, and embedding to enhance the understanding and applicability of data.
• Collaborate with cross-functional teams to integrate AI solutions into existing systems.
• Stay updated with the latest advancements in AI technologies, particularly relating to LLMs and agentic AI.
• Develop core logic, APIs, and use cases using Python.
• Leverage frameworks such as Langchain, Crewai, or other agentic AI frameworks for developing AI applications.
• Provide support and guidance to junior developers within the team.
Qualifications:
• 6-10 years of professional experience in backend development.
• Extensive experience with Python for developing backend solutions and AI use cases.
• Hands-on experience with Large Language Models (LLMs) and related technologies.
• Proficiency in data parsing, chunking, and embedding.
• Familiarity with agentic frameworks like Langchain or Crewai.
• Strong understanding of the latest technologies in LLMs and AI.
• Basic knowledge of Node.js is a plus.
• Strong problem-solving skills and ability to work in a fast-paced environment.
• Excellent communication and collaboration skills.