Principal AI Engineer

Company Description Cadence is a market leader in AI and digital twins, using advanced computational software to accelerate innovation in engineering design from silicon to complex systems. Guided by the Intelligent System Design™ strategy, Cadence provides essential design solutions that enable leading semiconductor and systems companies to develop next‑generation products across markets such as hyperscale computing, mobile communications, automotive, aerospace, industrial, life sciences, and robotics. The company’s technologies power the design of everything from individual chips to full electromechanical systems. In 2024, Cadence was recognized by the Wall Street Journal as one of the world’s top 100 best‑managed companies, highlighting its strong leadership and performance. Cadence offers broad opportunities for growth and impact in AI‑driven engineering—learn more at www.cadence.com.
Job Title: Principal AI Engineer — Agentic AI
Location: Bengaluru, India / Hybrid
Role Overview
We are looking for a visionary and hands-on Principal AI Engineer (Agentic AI) to lead the design, architecture, and production delivery of autonomous, multi-agent AI systems. You will bridge the gap between cutting-edge LLM/reasoning research and enterprise-grade, fault-tolerant software production. In this role, you will define how intelligent agents reason, plan, use tools, interact with persistent memory, and execute complex workflows reliably at scale.
Key Responsibilities
• Architecture & System Design: Own the end-to-end architecture for scalable, multi-agent ecosystems, defining clean interfaces, state management, and orchestration patterns.
• Agentic Workflows & Tool-Calling: Build and deploy autonomous agent loops capable of multi-step reasoning, dynamic tool/API calling, self-correction, and human-in-the-loop validation.
• Design and implement RAG and agentic AI systems.
• Reliability, Guardrails & Evaluation: Design robust evaluation harnesses, benchmarking pipelines, and safety guardrails to measure agent correctness, latency, cost, and anti-hallucination metrics.
• Production Integration: Integrate agentic frameworks deeply into existing cloud infrastructure, CI/CD pipelines, vector databases, and real-time telemetry systems.
• Technical Leadership & Mentorship: Act as a force multiplier across global engineering teams through design reviews, architectural guidance, and setting engineering standards for AI-native development.
Required Qualifications & Skills
• Experience: 8+ to 12+ years of software engineering experience, with a proven track record of shipping production AI/ML or LLM-driven autonomous systems.
• Core Programming: Advanced proficiency in Python (required) and strong foundational experience in systems languages like Java, C++, or Go.
• Agentic Frameworks: Hands-on mastery of modern agent orchestration and workflow frameworks such as LangGraph, CrewAI, LlamaIndex, or native LLM/Agent SDKs (OpenAI, Anthropic, Google Gemini).
• AI & Data Stack: Deep understanding of transformer architectures, prompt engineering, RAG (Retrieval-Augmented Generation), vector databases (e.g., Pinecone, Milvec, Qdrant), and embedding models.
• Evaluation & Observability: Experience with evaluation and tracing tools (e.g., LangSmith, Langfuse) and observability stacks (OpenTelemetry, Prometheus).
Infrastructure, Inference & MLOps: Mastery of containerization and orchestration platform tools (Docker, Kubernetes), cloud architectures, and specialized LLM inference engines (e.g., vLLM, TGI, TensorRT-LLM) to minimize Time-to-First-Token (TTFT) and inference latency.
• Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or equivalent practical industry experience.

Work arrangement
No