Gen AI Fullstack - Technical Architect

Iris Software, Inc.; Dadri; Vor Ort; INR 4.000.000 - 8.500.000; Vollzeit

Zusammenfassung

Iris Software in Noida is seeking a Gen AI Fullstack - Technical Architect to lead the architecture and delivery of enterprise-grade Generative AI and agentic AI solutions. You will own the technical vision from discovery to production, shaping scalable cloud-native deployments and collaborating with security, data, and engineering teams.

The role requires deep GenAI expertise, hands-on experience with LLMs, embedding models, and orchestration across Azure, AWS or GCP ecosystems, with strong

Qualifikationen

• Proven experience designing GenAI architectures with LLMs and multi-agent systems.

Aufgaben

• Design end-to-end GenAI, RAG, Agentic AI and multi-agent architectures.
• Define solution patterns covering LLMs, embeddings, vector databases, orchestration, APIs, data pipelines and enterprise integrations.
• Architect AI agents with tool calling, workflow orchestration, memory, Human-in-the-Loop and MCP-based integrations.
• Evaluate and select appropriate foundation models, AI platforms and architecture patterns based on quality, latency, security and cost.
• Establish LLMOps, evaluation, observability, guardrails and Responsible AI practices.

Kenntnisse

Agentic AI Systems

GenAI Framework Concepts

Cloud Application Integration

AI Agents Tool Calling

LangChain

AI Search Index

Tools

LangGraph

Semantic Kernel

Bedrock Agents/AgentCore

Jobbeschreibung

Job Overview

Gen AI Fullstack - Technical Architect

Location: Noida

Company: Iris Software

Role Purpose

• Lead the architecture and delivery of enterprise-grade Generative AI and Agentic AI solutions, translating business requirements into scalable, secure, and production-ready AI platforms.
• Own the technical vision from discovery and PoC through production deployment and optimization.

Key Responsibilities

• Design end-to-end GenAI, RAG, Agentic AI and multi-agent architectures.
• Define solution patterns covering LLMs, embeddings, vector databases, orchestration, APIs, data pipelines and enterprise integrations.
• Architect AI agents with tool/function calling, workflow orchestration, memory, Human-in-the-Loop and MCP-based integrations.
• Evaluate and select appropriate foundation models, AI platforms and architecture patterns based on quality, latency, security and cost.
• Design solutions using Azure OpenAI / Azure AI Foundry, Amazon Bedrock / AgentCore, Google Vertex AI or equivalent platforms.
• Establish LLMOps, evaluation, observability, guardrails and Responsible AI practices.
• Define scalable cloud-native deployment architectures using APIs, containers, Kubernetes, serverless and asynchronous/event-driven patterns.
• Ensure architecture meets enterprise requirements for security, privacy, resilience, scalability, compliance and cost optimization.
• Lead architecture workshops, technical design reviews, PoCs and solution demonstrations.
• Create reference architectures, technical standards and reusable accelerators for GenAI adoption.
• Partner with business, product, security, data and engineering stakeholders to drive solutions from use case identification to production adoption.

Mandatory Skills

• Agentic AI Systems, Advanced GenAI Agentic Framework Concepts, Cloud Application Integration Deployment, AI Agents Tool Calling, LangChain, AI Search Index

Required Skills

• Strong expertise in Generative AI, LLMs, Agentic AI and AI solution architecture.
• Hands-on experience with RAG, embeddings, vector search and semantic retrieval.
• Experience with agent frameworks such as LangGraph, LangChain, Microsoft Agent Framework, Semantic Kernel, Bedrock Agents/AgentCore or equivalent.
• Strong understanding of multi-agent orchestration, tool calling, context engineering, memory and Human-in-the-Loop patterns.
• Experience with one or more cloud AI ecosystems: Azure, AWS or GCP.
• Strong knowledge of Python, REST APIs, microservices and distributed/cloud-native architectures.
• Experience with LLM evaluation, tracing, monitoring, prompt/model versioning and LLMOps/MLOps.
• Understanding of AI security, guardrails, Responsible AI, identity/access management and data governance.
• Ability to assess architectural trade-offs across accuracy, latency, scalability, reliability and cost.