Senior / Lead Generative AI Application Architect (On-Site)

Location: Office-based (Full-Time, 100% In-Office)

Experience: 5–9 Years

Department: AI & Advanced Analytics Engineering

About The Role We are seeking a visionary and hands-on Generative AI Application Architect to lead the design and deployment of next-generation, AI-driven supply chain orchestration tools.

In this on-site role, you will bridge the gap between cutting-edge Large Language Models (LLMs), vector search technology, and complex supply chain execution systems. Working side-by-side with data scientists, backend developers, and product teams in our development center, you will build intelligent conversational interfaces, automated disruption-handling agents, and semantic search engines that help enterprises instantly navigate multi-tier supplier networks, freight data, and warehouse inventories.

Key Responsibilities & Detailed Breakdown: 1. GenAI Architecture & LLM Orchestration

- Design and implement enterprise-grade LLM architectures (leveraging models like GPT-4, Claude, and secured open-source weights such as Llama or Mistral) tailored for complex supply chain reasoning.
- Build advanced Retrieval-Augmented Generation (RAG) pipelines that safely ingest and query millions of unstructured documents, including supplier contracts, bills of lading, customs declarations, and carrier SLAs.
- Implement agentic AI workflows capable of multi-step reasoning (e.g., analyzing a port congestion alert, parsing inventory levels across regional warehouses, and drafting alternative freight routing recommendations).
- Vector Database & Semantic Search Integration
- Architect, optimize, and scale high-performance vector databases (such as Qdrant or Milvus) to enable sub-second semantic search across massive catalogs of parts, SKUs, historical shipments, and vendor profiles.
- Design efficient document chunking, metadata filtering, and embedding generation strategies specifically optimized for supply chain taxonomy and hierarchical product codes.




- Enterprise Data Governance & Security Compliance
- Enforce stringent data privacy and proprietary security frameworks, ensuring that sensitive enterprise supply chain data, pricing tiers, and vendor lists never leak across unauthorized public API boundaries.
- Build local guardrails, prompt-injection defense mechanisms, and output validation filters to guarantee hallucination-free, deterministic enterprise reporting.
- Cross-Functional Collaboration & Rapid Prototyping
- Lead physical whiteboarding sessions, architecture reviews, and rapid prototyping sprints with on-site engineering squads and client success teams.
- Partner directly with Data Engineers and Core Backend Engineers to expose AI capabilities via scalable, low-latency FastAPI microservices.
- Conduct live product demos and technical deep-dives with enterprise client stakeholders during on-site discovery workshops.

Required Skills & Qualifications

- Work Mode: 100% On-site commitment with daily physical attendance at our development hub.

- Core Technical Stack
- Advanced proficiency in Python (asyncio, FastAPI, Pydantic).
- Deep expertise in LLM frameworks (LangChain, LlamaIndex, Guidance).
- Hands-on experience with Vector Databases (Qdrant, Milvus, or Pinecone).
- Containerization & Orchestration tools (Docker, Kubernetes).
- Domain Experience: Strong foundational understanding of supply chain workflows (ERP/WMS data structures, inventory management, freight logistics, or procurement) is a significant advantage.
- System Design & Scaling: Proven track record of moving GenAI models from experimental Jupyter notebooks into fault-tolerant, high-concurrency production microservices.

Why Join Us In office? By working out of our central office, you will have immediate, face-to-face access to our core infrastructure teams and domain experts, allowing you to rapidly iterate on high-impact AI agents that directly influence global supply chain resilience. Skills: supply chain,kubernetes,fastapi,python,vector,langchain,freight,enterprise,application,llamaindex,docker

📌 Generative AI Application Architect (Supply Chain Analytics) (Gurugram)
🏢 HYrEzy Tech Solutions
📍 Gurugram