Role overview
**Core Responsibilities**
* Design and build advanced AI-driven systems utilizing LLMs (e.g., Azure OpenAI GPT
* Models, Claude, Llama, Mistral, Gemini, and open-source models) for tasks such as text understanding, generation, summarization, and contextual reasoning within engineering workflows.
* Architect and deploy agentic pipelines (multi-agent systems, autonomous LLM agents, chain-of-thought/reasoning systems) for process automation, decision support, and engineering knowledge orchestration.
* Develop and implement Advanced Retrieval-Augmented Generation (RAG) solutions - combining LLMs with vector databases, search engines, and enterprise knowledge sources for high-fidelity document analysis and Q&A.
* End-to-End automation of complex human-in-the-loop processes by chaining LLMs, expert systems, and external tools using orchestration frameworks (such as LangChain,
* LlamaIndex, Haystack, CrewAI, etc.).
* Evaluate, select, and integrate modern and emerging AI tools, APIs, and infrastructure
* (LLMOps, vector stores, document loaders, prompt management, agents frameworks, etc).
* Fine-tune, deploy, and monitor LLMs on private/in-house datasets to solve unique domain challenges and maintain compliance/privacy.
* Stay current with the fast-evolving AI landscape (open weights, small/efficient models, guardrails, synthetic data, evaluation techniques, multimodal models, etc.), and bring new approaches into the organization.
**Preferred:**
* Experience optimizing for model cost, latency, reliability, and scaling in production.
* Understanding of privacy, security, and compliance in LLM/AI applications (PII scrubbers, access controls, audit trails).
* Experience orchestrating multi-agent/agentic workflows (CrewAI, AutoGen, OpenAgents, etc.).
* Familiarity with CI/CD for AI pipelines, containerization (Docker), and cloud AI services (Azure ML, AWS Sagemaker, GCP Vertex).
**Qualification:**
* Bachelor’s in Electrical, Electronics, Computer science or Mechanical Engineering