Experience:

• 2–5 years of hands-on experience in AI/ML or applied AI engineering
• Experience building end-to-end AI systems (not just experimentation)
• Exposure to LLMs and AI agents in production environments

Qualification:

• Bachelor’s or Master’s in Computer Science, AI, Data Science, or related field

Responsibilities:

• Design and deploy multi-agent AI systems to orchestrate simulation workflows end-to-end
• Build LLM-powered agents with planning, memory, and tool usage capabilities
• Develop scalable agent orchestration pipelines using frameworks like LangGraph, AutoGen, CrewAI, or similar
• Integrate AI agents with simulation tools such as meshing, solvers, and data systems
• Connect AI agents with external APIs, databases, and internal engineering platforms
• Build production-ready AI systems for real-world engineering environments
• Develop Retrieval-Augmented Generation (RAG) pipelines using simulation data and technical documentation
• Implement vector databases and embedding models for domain-specific knowledge retrieval
• Monitor, debug, and optimise agent performance, latency, and cost
• Define evaluation frameworks to measure accuracy, reliability, and safety of AI decisions
• Implement guardrails to mitigate hallucination and failure scenarios
• Work closely with CAE and mechanical engineers to translate requirements into AI solutions
• Communicate complex AI concepts clearly to non-AI stakeholders

Nice to have:

• Experience with agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel
• Knowledge of RAG architectures and vector databases like Pinecone, ChromaDB
• Familiarity with MLOps tools including Docker, CI/CD, model serving frameworks
• Experience with structured outputs and function calling
• Exposure to CAE/FEA tools such as ANSYS, Abaqus, LS-DYNA

More skills:

LLMs (OpenAI, open-source models), Agent-based systems, Tool integration, Cloud platforms (preferably GCP), Software engineering best practices (testing, version control)

Other:

• Hybrid work type
• Core competencies include agentic system design (planning, memory, orchestration), prompt engineering and LLM optimisation, reliability engineering and AI safety practices, strong analytical thinking and problem-solving, and effective cross-functional communication