Project Role : Application Support Engineer
Project Role Description : Act as software detectives, provide a dynamic service identifying and solving issues within multiple components of critical business systems.
Must have skills : Python (Programming Language)
Good to have skills : NA
Minimum
12 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
As an Application Support Engineer, you will act as software detectives, providing a dynamic service that identifies and solves issues within multiple components of critical business systems. Your typical day will involve collaborating with various teams to troubleshoot and resolve software-related challenges, ensuring the smooth operation of essential applications. You will engage in problem-solving activities, analyze system performance, and contribute to the continuous improvement of processes and systems, all while maintaining a focus on delivering high-quality support to users and stakeholders.
We are seeking a visionary SRE Lead with 15+ years of experience to spearhead the implementation of our strategic automation blueprint. This role sits at the intersection of high-scale reliability and Generative AI. You will lead a team of 6–9 engineers to build a self-healing infrastructure where Agentic AI—guided by sophisticated Prompt Engineering—diagnoses and remediates system issues in real-time. You will use tools like Vertex AI or Amazon Bedrock to move beyond static scripts into dynamic, reasoning-based automation.
Roles & Responsibilities:
- Architect & Implement: Execute the Automation Blueprint, transitioning from manual scripts to agentic workflows that can perceive, reason, and act.
- Prompt Engineering & Strategy: Design, test, and optimize complex prompt templates (Chain-of-Thought, React) that guide SRE agents through troubleshooting workflows.
- Leadership: Directly manage and mentor a team of 6–9 SREs, establishing best practices for Prompt Ops (versioning and evaluating prompts like code).
- AI Integration: Build autonomous SRE Agents using Vertex AI or Bedrock that can interface with APIs, query logs, and execute terraform changes safely.
- Python Mastery: Lead the development of the Python-based glue code that connects LLMs to our production telemetry and orchestration layers.
- Prompt Engineering Expertise: Deep understanding of how to structure prompts to minimize hallucinations and maximize deterministic outcomes in high-stakes production environments.
- AI/ML Proficiency: Hands-on experience with LLM orchestration frameworks (e.g., LangChain, CrewAI, or Haystack) and cloud AI services (Vertex AI or Bedrock).
- Expert Coding: Advanced Python skills are essential for building the frameworks that wrap around your AI prompts. The SRE Mindset : A drive to ensure that while the automation is agentic, the guardrails remain absolute.
- Expected to be an SME.
- Collaborate and manage the team to perform.
- Responsible for team decisions.
- Engage with multiple teams and contribute on key decisions.
- Expected to provide solutions to problems that apply across multiple teams.
- Facilitate knowledge sharing sessions to enhance team capabilities.
- Monitor system performance and proactively address potential issues.
Professional & Technical Skills:
- Must To Have Skills: Proficiency in Python (Programming Language).
- Good To Have Skills: Experience with cloud platforms such as AWS or Azure.
- Strong understanding of software debugging techniques.
- Familiarity with version control systems like Git.
- Experience in developing and maintaining automated testing frameworks.
Additional Information:
- The candidate should have minimum 12 years of experience in Python (Programming Language).
- This position is based at our Bengaluru office.
- A 15 years full time education is required.
