AI Engineer - LLM/ RAG/ Agentic Workflow (3 to 4yrs)

Silicon Labs (NASDAQ: SLAB) is the leading innovator in low-power wireless connectivity, building embedded technology that connects devices and improves lives. Merging cutting-edge technology into the world’s most highly integrated SoCs, Silicon Labs provides device makers the solutions, support, and ecosystems needed to create advanced edge connectivity applications. Headquartered in Austin, Texas, Silicon Labs has operations in over 16 countries and is the trusted partner for innovative solutions in the smart home, industrial IoT, and smart cities markets. Learn more at www.silabs.com.

Role Overview:

We are seeking a AI Engineer to design, build, and scale production‑grade AI applications, including Retrieval‑Augmented Generation (RAG) systems and agentic, automated workflows. The ideal candidate will own solutions end‑to‑end—from architecture and model orchestration to deployment, monitoring, and continuous optimization in production environments.

This role requires deep expertise in LLMs, vector databases, orchestration frameworks, cloud infrastructure, and MLOps, with a strong engineering mindset to deliver reliable, secure, and scalable AI systems.

Key Responsibilities

AI Application Development

• Design and implement RAG-based applications using state-of-the-art LLMs (OpenAI, Azure OpenAI, Anthropic, open-source models).
• Build agentic systems capable of planning, tool usage, memory management, and autonomous task execution.
• Develop multi-agent and workflow-driven automation for complex business processes.
• Optimize prompt engineering, context management, and response quality.

Architecture & Scaling

• Architect high-performance, scalable AI systems capable of handling enterprise workloads.
• Design token-efficient, low-latency pipelines with strong cost controls.
• Implement caching, re-ranking, chunking strategies, and hybrid retrieval (semantic + keyword).

Production Deployment & Operations

• Deploy AI applications to production using cloud-native architectures.
• Ensure high availability, observability, and fault tolerance.
• Implement logging, tracing, evaluation metrics, guardrails, and feedback loops.
• Handle model lifecycle management, versioning, and rollback strategies.

Data, Security & Governance

• Implement secure ingestion pipelines across structured and unstructured data sources.
• Ensure data privacy, compliance, and access controls.
• Apply content moderation, safety filters, and hallucination mitigation techniques.

Collaboration & Leadership

• Collaborate with product managers, backend engineers, and data teams.
• Translate business requirements into robust AI solutions.
• Mentor junior engineers and contribute to AI best practices.

Required Skills & Qualifications

Core AI & LLM Expertise

• Strong experience with LLMs (All GPT models, Claude, LLaMA, Mistral, etc.).
• Hands-on experience building RAG pipelines end‑to‑end.
• Solid understanding of embeddings, vector similarity search, re-ranking, and context windows.
• Experience with agentic frameworks (LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel).

Backend & Data Engineering

• Proficiency in Python (required) and familiarity with FastAPI/Flask.
• Experience with vector databases (Pinecone, Weaviate, FAISS, Milvus, Qdrant).
• Knowledge of data preprocessing, document chunking, metadata indexing.

Machine Learning Expertise

• Strong foundation in machine learning algorithms and statistics.
• Experience with scikit-learn, XGBoost, LightGBM, PyTorch or TensorFlow.
• Knowledge of model evaluation, cross-validation, metrics, and error analysis.
• Experience deploying ML models into production environments.
• Understanding of ML lifecycle management and model drift.

Cloud, DevOps & MLOps

• Strong experience with AWS / Azure / GCP (Azure OpenAI preferred).
• Containerization and orchestration using Docker and Kubernetes.
• CI/CD pipelines for AI applications.
• Monitoring tools for AI systems (prompt + model performance monitoring).

Production Readiness

• Experience deploying AI solutions in real-world production environments.
• Understanding of latency, throughput, cost optimization, and reliability.
• Familiarity with evaluation frameworks and A/B testing for LLM outputs.

Preferred / Nice-to-Have Skills

• Experience with fine-tuning or parameter-efficient tuning (LoRA, PEFT).
• Knowledge of multi-modal models (text + image).
• Experience with enterprise search, knowledge graphs, or document AI.
• Background in distributed systems or high-scale backend services.
• Exposure to compliance standards (SOC2, ISO, GDPR).

Benefits & Perks

Not only will you be joining a highly skilled and tight-knit team where every engineer makes a significant impact on the product; we also strive for good work/life balance and to make our environment welcoming and fun.

• Equity Rewards (RSUs)

• Employee Stock Purchase Plan (ESPP)

• Insurance plans with Outpatient cover

• National Pension Scheme (NPS)

• Flexible work policy

• Childcare support

Silicon Labs is an equal opportunity employer and values the diversity of our employees. Employment decisions are made on the basis of qualifications and job-related criteria without regard to race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status, or any other characteristic protected by applicable law.