VuNet Systems - Architect - Generative AI/Agentic AI

Description :

Role : GenAI / Agentic AI / SLM Architect

Education : B.E/M.Tech (CSI/IT/Data Science)

Location : Bengaluru (Work from Office)

Experience : 8 - 12 years

Your Role : GenAI / Agentic AI / SLM Architect

We are hiring a GenAI and Agentic AI Architect to lead the design and delivery of our AI-powered diagnostics layer. This includes on-premise LLM deployment, agentic workflows for root cause analysis, and small language model (SLM) integration for real-time intelligent troubleshooting. The ideal candidate has shipped AI-powered product features from an engineering or architecture role, not just research.

Key Responsibilities :

- Architect the on-premise LLM and SLM deployment infrastructure for secure enterprise environments where cloud AI services cannot be used.

- Design agentic AI workflows for automated root cause analysis, incident correlation, and intelligent alert triage.

- Build and optimize RAG (Retrieval-Augmented Generation) pipelines for enterprise knowledge bases, runbooks, and operational documentation.

- Design the integration layer between AI models and the observability platform (traces, logs, metrics, topology data).

- Establish MLOps practices for model lifecycle management, versioning, evaluation, fine-tuning, and deployment in air-gapped environments.

- Architect prompt engineering frameworks, guardrails, and output validation systems for production reliability.

- Drive adoption of AI-assisted capabilities across APM, log analytics, infrastructure monitoring, and business journey monitoring.

- Evaluate and select foundation models, embedding models, and vector databases for the platform stack.

Mandatory Skills :

- 8+ years in software engineering with at least 3 years focused on AI/ML systems in a product engineering role.

- Hands-on experience building and shipping GenAI or LLM-powered product features to production (not just POCs or demos).

- Deep understanding of LLM inference optimization, quantization, and on-premise deployment (vLLM, TGI, Ollama, or equivalent).

- Experience with agentic frameworks (LangChain, LangGraph, CrewAI, AutoGen, or custom agent architectures).

- Strong background in RAG pipelines, vector databases (Milvus, Weaviate, ChromaDB), and embedding models.

- Proficiency in Python and experience with ML infrastructure (GPU management, model serving, batch vs. real-time inference).

- Understanding of security and compliance requirements for AI in regulated industries.

Preferred / Nice-to-Have :

- Experience in observability, AIOps, or ITOps domains.

- Background in deploying AI systems in air-gapped or highly restricted enterprise environments.

- Experience with classical ML for anomaly detection, forecasting, and alert correlation alongside GenAI capabilities.