Engineer III - AI Powered SRE (UK Shift Timing)
CrowdStrike12 hours ago
Bengaluru, IndiaSenior
Responsibilities
- Develop AI agents that detect, diagnose, and remediate operational issues across bare-metal servers and virtual machines.
- Document operational toil and build event-driven automation pipelines using LLMs and agentic frameworks.
- Integrate agentic workflows with ELK, Prometheus, Grafana, and other monitoring and telemetry systems.
- Support AI-assisted incident response, signal correlation, remediation recommendations, incident analysis, and post-incident reviews.
- Support platform operations involving availability, latency, throughput, monitoring, and issue response.
- Instrument and evaluate agent performance and establish feedback loops to improve accuracy and reliability.
- Gather and analyze operating-system and application metrics for AI models, agents, performance tuning, and predictive operations.
- Maintain technical documentation for automation systems, agent workflows, and operational runbooks.
- Collaborate with globally distributed engineers and contribute to shared automation solutions.
Requirements
- Bachelor's degree and/or equivalent experience in Computer Science, Engineering, or a related field.
- 5+ years of software engineering experience with exposure to systems and infrastructure concepts.
- 5+ years of hands-on experience with one or more of Python, Go, Java, or C++, with Python strongly preferred.
- Foundational experience or strong interest in AI agents or LLM-powered automation, including prompt engineering, tool/function calling, and retrieval-augmented generation.
- Familiarity with LangChain, LlamaIndex, AutoGen, CrewAI, or equivalent agentic frameworks.
- Experience integrating automation with ticketing systems, monitoring platforms, or CI/CD pipelines.
- Working knowledge of Linux engineering and administration.
- Familiarity with Linux, VMware, Docker, Kubernetes, or related infrastructure platforms.
- Familiarity with ELK, Prometheus, or Grafana monitoring and telemetry stacks.
- Familiarity with Puppet, Chef, Ansible, or equivalent configuration management tools.
- Solid understanding of software engineering fundamentals and Kubernetes, with interest in distributed systems.
- Experience using AI technologies to improve decision-making, workflows, efficiency, and business outcomes.
- Preferred qualifications include MLOps or AI observability experience with LangSmith, Weights & Biases, or Arize; exposure to SRE, Platform Engineering, or DevOps; self-healing infrastructure or autonomous remediation experience; and contributions to open-source AI or SRE tooling.
Benefits
- Market-leading compensation and equity awards are offered.
- Comprehensive physical and mental wellness programs are provided.
- Competitive vacation and holidays are available.
- Paid parental and adoption leave is provided.
- Professional development opportunities are available to all employees.
- Employee Networks, geographic neighborhood groups, and volunteer opportunities support community building.
- The company offers a vibrant office culture with world-class amenities.
- CrowdStrike is Great Place to Work Certified globally.
Categories
AI ApplicationsSite Reliability
About CrowdStrike
CrowdStrike builds the Falcon cloud-native security platform used by enterprises and governments to protect endpoints, cloud workloads, identities, and data with EDR, next-generation antivirus, threat intelligence, and managed threat hunting. Founded in 2011 and publicly traded on NASDAQ as CRWD, the company sells primarily by subscription and also provides incident response services; its systems ingest and analyze nearly 3 trillion security events per day across customer environments.