Hungry, Humble, Honest, with Heart.

 

The Opportunity

 

About the Team

The Panacea team has a passionate set of engineers across India and US office. We move fast, collaborate closely, and care deeply about quality and ownership. Our mission is to deliver AI/ML-powered developer productivity tools that solve real engineering and support pain points at scale.

Why Join Us
 

• Work along with high-impact team delivering AI-first observability tools that directly improve engineering velocity and product quality.
• Tackle challenging technical and product problems at scale and speed.
• Shape the foundational AI platform and practices across Nutanix.
• Enjoy the flexibility of hybrid work, with a culture that values deep work, collaboration, and ownership.
• Be part of a startup-style team backed by the scale, reach, and stability of a global cloud leader.

 

Your Role

• Auto RCA Engine: Deliver an AI-driven engine that correlates logs and metrics across distributed services, automatically surfacing explanations for incidents. This includes an agentic platform that integrates MCP servers as tools, alongside a chat-like conversational interface that enables engineers to query issues, run diagnostics, and collaborate on RCA in natural language. Here, LLMs will power interactive diagnostics and human-like discussions around problem-solving.
• AI-Powered Observability Platform: Own the vision, architecture, and delivery of Panacea’s ML-based log and metrics analyzer that reduces triage time and improves engineering efficiency. This includes leveraging LLMs for anomaly explanation, RCA summaries, and contextual recommendations to engineers and support teams.
• Knowledge Base Creation: Build a robust company-wide knowledge base that consolidates product, observability, and system data into structured formats. This knowledge base will serve as a foundation for LLMs, enhancing their ability to reason, answer queries, and provide deeper insights into system anomalies.
• Metrics Anomaly Detection: Development of models that detect anomalies in CPU, memory, disk I/O, network traffic, and service health, enabling proactive identification of performance regressions. LLMs will assist in summarizing anomalies and providing contextual recommendations for remediation.
• Feedback Loop & Continuous Learning: Build infrastructure that captures user interactions and feedback, using LLMs and ML pipelines to retrain and improve anomaly detection and RCA accuracy over time.
• Central AI Charter: Collaborate with product and support teams to define foundational AI infrastructure, shared ML components, governance practices, and standards that scale across Nutanix’s product ecosystem.

Responsibilities
 

• Apply expertise in LangGraph, LangChain, agentic AI architectures, and multi-agent orchestration to build intelligent, scalable workflows.
• Design and develop conversational AI systems (chatbots, copilots, or support assistants) for incident triage and RCA.
• Implement correlation models to connect anomalies across logs and metrics, forming a cohesive RCA narrative.
• End-to-end ML lifecycle: data ingestion, feature extraction, model training, evaluation, deployment, and monitoring.
• Build explainable AI systems that increase adoption and trust within engineering, QA, and support teams.
• Collaborate with cross-functional stakeholders (SRE, QA, Dev) to deeply understand pain points and translate them into intelligent tooling.

 

What You Will Bring

• • Educational Background: B.Tech/M.Tech in Computer Science, Machine Learning, AI, or a related field.
  • Experience: 6+ years in software engineering, with a track record of designing, developing, and deploying AI/ML systems at scale,
  • AI/ML Expertise:
  • Strong in time-series anomaly detection, statistical modeling, supervised/unsupervised learning.
  • Experience building ML models for metrics data (CPU, memory, IOPS, network, etc.) using models like Isolation Forest, Prophet, LSTM, or deep autoencoders.
  • Experience with LLMs for downstream tasks like summarization, root cause reasoning, or intelligent Q&A.
  • Preferred experience in designing and deploying agentic workflows.
  • Engineering Skills: Strong Python programming skills with proficiency in ML libraries (PyTorch, TensorFlow, Scikit-learn), time-series frameworks, and MLOps tools. Experience building and operating robust data pipelines and serving models at scale.
  Observability Knowledge: Familiarity with logs, metrics, and traces, along with monitoring tools such as Prometheus, Grafana, and ELK

 

Work Arrangement

Hybrid: This role operates in a hybrid capacity, blending the benefits of remote work with the advantages of in-person collaboration. For most roles, that will mean coming into an office a minimum of 3 days per week, however certain roles and/or teams may require more frequent in-office presence. Additional team-specific guidance and norms will be provided by your manager.

 

--