Job Description

• Agentic AI Development: Design, build, and optimize AI agents capable of reasoning, planning, and executing tasks within ERP/MES environments.
• Integration with ERP/MES Systems: Ensure seamless interaction between AI agents and core ERP/MES modules (procurement, warehouse, production, sales, etc.).
• AI Architecture & Frameworks: Architect scalable AI frameworks that balance performance, reliability, and cost-efficiency (e.g., token-controlled architecture).
• Applied Machine Learning: Train, fine-tune, and optimize models (LLMs, RAG, multi-agent systems) for domain-specific tasks in manufacturing and supply chain operations.
• Experimentation & Research: Stay ahead of emerging AI technologies (LangGraph, MCP, agent orchestration frameworks, RPA, etc.) and evaluate their practical adoption.
• Testing & Validation: Ensure AI models and agents are rigorously tested for accuracy, stability, and enterprise readiness.
• Collaboration: Work closely with product, engineering, and business teams to translate requirements into intelligent system design.

Job Requirements

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• 4–5 years of hands-on experience in AI/ML engineering, with proven experience in building AI-driven applications.
• Strong background in machine learning, NLP, LLMs, or multi-agent systems.
• LangGraph expertise: Built production-ready graphs with multi-agent workflows, conditional logic, checkpointers, and error handling.
• LangGraph expertise: Designed tool nodes for ERP/MES actions with idempotency, retries, and observability (token usage, latency, cost).
• LangGraph expertise: Implemented policy/routing nodes (RBAC checks, approval gates, cost controllers).
• Context Engineering skills: Architected retrieval pipelines (BM25 + embeddings + metadata filters) with tenant-level security and domain-specific chunking (SOPs, BOMs, routings, QC docs).
• Context Engineering skills: Designed memory layers (working scratchpads, session summaries, long-term semantic knowledge).
• Context Engineering skills: Built grounded tool schemas (strict JSON, validators, reconciliation with ERP ledgers).
• Context Engineering skills: Applied cost & performance controls (caching, rerankers, token budgeting, tiered model routing).
• Proficiency in Python (PyTorch, TensorFlow, LangChain, RAG pipelines).
• Experience deploying on cloud platforms (AWS, GCP, or Azure) with Docker/Kubernetes.
• Familiarity with Agile methodologies and ability to drive Agile AI development practices.
• Entrepreneurial mindset: resourceful, adaptable, and driven to create impactful solutions with limited resources.

Skills