AI / Agentic AI Engineer - Enterprise Observability

Overview The Enterprise Observability team is responsible for monitoring, maintaining, and improving the health of critical banking applications, services, and infrastructure. As observability platforms generate massive volumes of metrics, events, logs, traces, and synthetic monitoring data, operational teams require intelligent solutions to identify, correlate, and remediate issues rapidly.

We are seeking an experienced AI / Agentic AI Engineer to design and develop next-generation AI-powered observability solutions that transform operational monitoring into proactive, intelligent, and increasingly autonomous systems.

This role will focus on building Agentic AI and RAG-based platforms capable of analyzing operational telemetry data, accelerating incident investigations, reducing alert fatigue, recommending corrective actions, and enabling self-healing capabilities across enterprise banking environments.

Key Responsibilities

Agentic AI Development

- Design and develop enterprise-scale Agentic AI solutions for observability and operational workflows.
- Build autonomous and semi-autonomous agents capable of incident investigation and remediation.
- Implement multi-agent frameworks using LangGraph, LangChain, Microsoft AutoGen, and OpenAI Agents SDK.
- Develop AI orchestration workflows that support operational decision-making.

RAG & Knowledge Engineering
- Design Retrieval Augmented Generation (RAG) architectures for operational intelligence.
- Build and manage enterprise knowledge repositories and incident knowledge bases.
- Develop solutions leveraging vector databases such as:

- Azure AI Search

- Pinecone

- Weaviate

- ChromaDB
- Implement incident knowledge graphs and context-aware retrieval systems.

Observability & AIOps
- Analyze Metrics, Events, Logs, Traces, and Synthetics (MELTS) data across multiple observability platforms.
- Develop AI-driven root cause analysis and anomaly detection solutions.




- Create intelligent alert correlation and incident prioritization mechanisms.
- Enable proactive issue detection and predictive analytics capabilities.

Automation Engineering
- Develop operational runbooks and automated remediation workflows.
- Build self-healing automation solutions using:

- Python

- PowerShell

- REST APIs

- Workflow orchestration tools
- Integrate AI systems with observability and IT operations platforms.
- Drive improvements in operational efficiency and Mean Time to Resolution (MTTR).

Stakeholder Collaboration
- Partner with Observability, SRE, Infrastructure, Platform Engineering, and Operations teams.
- Translate business and operational requirements into AI-powered solutions.
- Contribute to strategic initiatives focused on operational resilience and service reliability.

Required Skills & Experience

Core Technical Skills

- Strong experience in Agentic AI solution development.
- Expertise in LangChain, LangGraph, Microsoft AutoGen, Azure AI Foundry, and OpenAI Agents SDK.
- Hands-on experience designing and implementing RAG architectures.
- Experience with vector databases including Pinecone, Weaviate, ChromaDB, or Azure AI Search.
- Robust programming skills in Python.

Automation & Integration
- Experience building remediation workflows and operational automation solutions.
- Hands-on experience with REST APIs and orchestration frameworks.
- Knowledge of PowerShell and automation scripting.

Observability & Operations
- Understanding of observability concepts including Metrics, Logs, Events, Traces, and Synthetic Monitoring.
- Experience supporting AIOps, Site Reliability Engineering (SRE), IT Operations, or Platform Engineering environments.
- Knowledge of incident management and operational excellence practices.

Preferred Qualifications
- Banking or Financial Services experience.
- Experience with Enterprise Observability platforms.
- Knowledge of SRE, AIOps, and IT Service Management (ITSM) environments.
- Experience building AI solutions for operational intelligence or production support organizations.
- Exposure to cloud platforms such as Azure, AWS, or GCP.

📌 AI Engineer (Bengaluru)
🏢 Allegis Group
📍 Bengaluru