Key Responsibilities

- Implement Specialized Agents: Build out the functional logic for the Triage Agent (mapping incidents to a live Skills Matrix), the RCA Agent (deep log analysis and structured synthesis), and the Learning Agent (synthesizing closed tickets into vector memory).
- Develop Topology-Aware Contextual Pipelines: Implement the ingestion pipelines that extract cluster topologies from Kubernetes and cloud infrastructure APIs, converting them into nodes and edges within our Knowledge Graph.
- Tool Engineering & API Binding: Develop reliable Python-based tools and functions that agents use to query Datadog metrics, scrape Splunk logs, extract network paths from graph databases, interact with Kubernetes clusters via kubectl APIs, and update ServiceNow ticket fields.
- Graph RAG & Pipeline Execution: Implement chunking strategies, metadata tagging, and hybrid graph/vector retrieval logic to ensure the Auto-Remediation agent retrieves identical past resolutions based on system context, not just keyword matching.
- Structured Output Engineering: Utilize Pydantic and function-calling mechanics to enforce strict JSON schemas on agent outputs, making certain that the RCA summaries and ticket updates are entirely deterministic.
- State Management:



Write clean edge-transition logic inside our LangGraph state machines to seamlessly pass incident contexts between the orchestrator and specialized agents.

Required Technical

Skills

- Languages & Frameworks: Strong proficiency in Python, asynchronous programming, and frameworks like FastAPI and Pydantic.
- AI & Graph Stack: Hands-on experience with LLM APIs, function calling, structured extraction, and agent patterns.

Experience constructing, updates, and querying Knowledge Graphs (using Cypher/SQL) for data retrieval is highly preferred.

- Data & APIs: Robust experience working with SQL (PostgreSQL), writing complex filtering queries, and consuming complex enterprise REST APIs with robust error/timeout handling.
- DevOps/Infra Familiarity: Comfort with basic Docker containerization, CI/CD pipelines, and navigating infrastructure maps (Kubernetes namespaces, VPC layouts, service meshes) in cloud environments.

Experience & Qualifications

- 4+ years of software engineering experience, with 1+ years focused on integrating LLMs, building RAG pipelines, or maintaining Graph/Relational data systems.
- Practical exposure to Graph databases or building data pipelines that map relational dependencies (e.g., dependency trees, network routing tables, or software architecture graphs).
- A background or strong interest in DevOps, site reliability engineering (SRE), or backend systems automation is a massive advantage.

📌 AI Automation Roles - Sr Software Developer (Gurugram)
🏢 AIonOS
📍 Gurugram