Job Title/Role : AI – Lead - Agentic AI & Autonomous Supply Chain Systems

Location : Bangalore (On-site)

Required Academics :Bachelor’s or Master’s degree in Computer Science, Engineering, or a related technical field.

Interview Mode : Face to Face Interview Only

Required Skills & Experience

- 5+ years of software engineering experience.
- 2+ years of hands-on experience building GenAI and Agentic AI applications, preferably in production enterprise environments.

• Preferred experience in supply chain, logistics, transportation, warehouse management,

procurement, manufacturing, or enterprise SaaS.

- Demonstrated experience building production-grade AI systems.
- Experience taking AI systems from:

POC → Pilot → Production → Scale
- Experience building autonomous workflows or AI agents capable of tool usage and multi-step execution.
- Experience integrating AI systems with enterprise APIs, databases and business applications.
- Experience with AI platform engineering, intelligent automation, enterprise AI, or similar systems.

Caliper Business Solutions (SCLEN.AI) is technology-driven enterprise software company that orchestrates supply chain and logistics execution networks through our intelligent digital platforms. Our solutions enable enterprises, ecosystem service providers, and end users to plan, execute, monitor, analyze, optimize, and orchestrate end-to-end supply chain and logistics operations with real-time visibility, intelligence,

and control.

Our platform enables:

- Multi-enterprise supply chain orchestration
- Procurement-to-pay and order-to-delivery lifecycle management
- Supplier onboarding and procurement optimization
- Warehousing and inventory management
- Multimodal transportation management
- In-plant logistics and yard management
- Real-time visibility and execution control
- AI-driven operational intelligence and workflow automation

We are actively transforming our platform ecosystem with:

- GenAI-powered enterprise workflows
- Agentic AI orchestration platforms
- AI copilots for operations and decision-making
- Autonomous workflow execution systems
- Multi-agent coordination frameworks
- Predictive and prescriptive intelligence
- Real-time operational analytics
- Intelligent supply chain automation

Our engineering organization focuses on building scalable, cloud-native, AI-first enterprise platforms capable of orchestrating complex supply chain and logistics ecosystems across shippers, suppliers, logistics partners, distributors, and customers.

About the Role

We are looking for a highly hands-on AI Lead – Agentic AI & Autonomous Supply Chain Systems to lead the architecture, development, deployment, and evolution of next generation AI capabilities across SCLEN.AI.

The ideal candidate will be capable of taking an enterprise business problem and designing an AI system that can:

Understand → Reason → Plan → Act → Observe → Learn/Adapt → Escalate The candidate will architect and build intelligent agents, multi-agent systems, AI copilots, RAG systems, autonomous workflows, AI decision systems, and the underlying AI platform required to deploy these capabilities reliably at enterprise scale.

The role requires a solid combination of:

- AI/LLM engineering
- Agentic AI architecture




- Backend engineering
- Enterprise systems integration
- Workflow orchestration
- AI evaluation and observability
- Cloud-native engineering
- Technical leadership
- Strong understanding of supply-chain and enterprise workflows The candidate is expected to remain hands-on, contributing directly to architecture, coding, experimentation, prototyping, production deployment, optimization, and technical decision-making.

Key Responsibilities:

1. Agentic AI & Multi-Agent Systems

- Design, develop, and deploy production-grade autonomous AI agents for enterprise applications.
- Build AI agents capable of planning, task decomposition, tool selection, workflow execution, context management, and decision-making.
- Develop multi-agent systems with agent delegation, coordination, shared memory, and agent-to-agent communication.
- Implement agent architectures such as Planner–Executor, Supervisor–Worker, and Human-in-the-Loop systems.

2. Autonomous Supply Chain Workflows

- Develop AI-driven autonomous workflows for procurement, supplier management, purchase orders, transportation, shipment execution, inventory, warehousing, and logistics.
- Build AI agents capable of detecting issues, diagnosing root causes, recommending actions, executing workflows, and escalating exceptions.
- Integrate AI solutions with supply chain operations to improve automation, efficiency, and decision-making.

3. Enterprise Integration & AI Copilots

- Develop AI copilots for logistics, operations, customer service, analytics, and decision support.
- Integrate AI agents with enterprise systems such as ERP, TMS, WMS, CRM, and external APIs.
- Implement function calling, tool calling, API orchestration, database access, and workflow automation.
- Ensure secure execution through authorization, validation, approval workflows, and auditability.

4. RAG & Knowledge Systems

- Design and implement enterprise-grade Retrieval-Augmented Generation (RAG) systems.
- Work with structured and unstructured data, including documents, SOPs, contracts, policies, and operational records.
- Implement embeddings, semantic search, hybrid search, reranking, context selection, and knowledge retrieval.
- Develop agent memory systems supporting short-term memory, long-term memory, workflow state, and enterprise context.

5. AI Evaluation, Reliability & LLMOps

- Establish frameworks to evaluate AI agents based on task success, decision accuracy, tool-call performance, reliability, and business outcomes.
- Implement regression testing, scenario testing, red-team testing, and end-to-end workflow testing.
- Develop AI observability systems to monitor prompts, model responses, agent trajectories, tool calls, latency, failures, and token usage.
- Implement AI guardrails, governance, and human escalation mechanisms to ensure secure and reliable AI operations.

6. AI Platform Architecture





- Architect scalable and reusable AI services, microservices, agent frameworks, tool registries, memory services, and RAG platforms.
- Design asynchronous, event-driven, and long-running AI workflows.
- Develop model routing strategies based on task complexity, cost, latency, privacy, and reliability.
- Establish reusable AI engineering standards across SCLEN.AI products.

7. Technical Leadership

- Provide technical leadership, mentorship, and guidance to AI engineers.
- Conduct architecture reviews, technical design reviews, and establish best practices for AI development.
- Collaborate with Product, Engineering, Data, UX, and Business teams.
- Translate business requirements into scalable AI-native architectures and enterprise solutions.

Technical Skills

Programming & Backend Engineering

- Strong hands-on experience in Python, FastAPI/Django/Flask, REST APIs, asynchronous programming, and microservices.
- Experience with MongoDB and enterprise databases.
- Strong understanding of distributed systems and scalable backend architecture.

GenAI & Agentic AI

- Strong knowledge of LLMs, Transformer models, AI agents, multi-agent orchestration, planning, task decomposition, and tool/function calling.
- Experience with RAG, prompt engineering, context engineering, agent memory, state management, and structured outputs.
- Familiarity with frameworks such as LangGraph, LangChain, CrewAI, LlamaIndex, AutoGen, or Semantic Kernel.

LLM Ecosystem

- Experience working with OpenAI APIs, Anthropic, Google Gemini, Llama, Mistral, DeepSeek, or other commercial/open-source models.
- Ability to evaluate and select appropriate models based on quality, cost, latency, and reliability.

Databases & Retrieval

- Experience with vector databases such as Pinecone, Weaviate, Chroma, or FAISS.
- Knowledge of Elasticsearch/OpenSearch, semantic search, hybrid search, reranking, and knowledge retrieval.
- Exposure to graph databases and knowledge graphs.

Cloud & DevOps

- Strong experience with Docker, Kubernetes, CI/CD, cloud-native deployments, and distributed systems.
- Experience with AWS, Azure, or Google Cloud.
- Knowledge of AI observability, monitoring, logging, and tracing.
- Experience building autonomous enterprise AI workflows and multi-agent systems.
- Experience integrating AI agents with enterprise applications and APIs.
- Knowledge of AI evaluation, LLMOps, observability, and governance.
- Experience with event-driven and asynchronous AI architectures.
- Exposure to fine-tuning, embeddings, model optimization, and advanced AI planning.
- Strong understanding of AI security, authorization, and auditability.

Success Expectations Within the first 3–6 months, the AI Lead should be able to:

- Establish the foundational Agentic AI architecture.
- Develop and deploy production-grade AI agents for supply chain use cases.
- Build reusable AI infrastructure covering agent orchestration, RAG, memory, evaluation, and observability.
- Establish AI engineering standards for development, testing, monitoring, and governance.
- Deliver measurable business improvements through automation, faster exception resolution, improved service levels, and reduced manual intervention.

Send your resume to [email protected]

📌 AI Lead (Bengaluru)
🏢 SCLEN.AI
📍 Bengaluru