Senior AI Engineer

Key Responsibilities

• Architect & Build RAG Systems: Design, develop, and deploy sophisticated Retrieval-Augmented Generation (RAG) systems to power our next-generation search and discovery experience.
• Develop & Fine-Tune LLMs: Lead the development of advanced generative models for nuanced tasks like automated content creation, summarization, and metadata enrichment.
• Own the Gen AI Stack: Select, provision, and optimize our stack, leveraging managed services like Azure OpenAI or AWS Bedrock, or self-hosting models on GPU infrastructure. You will establish best practices for repo structure, CI/CD, and model/prompt versioning.
• Implement LLMOps: Embed robust observability using tools like OpenTelemetry and Prometheus. This includes tracking standard metrics (latency, cost, accuracy) and specialized monitoring for hallucination, toxicity, and data drift.
• Lead & Mentor: Hire, coach, and develop ML talent. Set the standard for high-quality code, rigorous experimentation, and rapid iteration within the Gen AI domain.

Must-Have Skills

• Production LLM Experience: 5+ years in Python with demonstrable success in productionizing LLM applications using modern frameworks like DSPY, LangChain, LlamaIndex, or Hugging Face Transformers.
• RAG Expertise: Deep, practical knowledge of RAG architecture, including advanced prompt engineering, chunking strategies, and proficiency with vector databases (e.g., Pinecone, Weaviate, Milvus).
• Cloud Proficiency: Expertise with managed LLM services (Azure OpenAI Service or AWS Bedrock). Strong foundational cloud skills in either Azure or AWS for compute orchestration (AKS/EKS), serverless functions, and storage.
• MLOps Acumen: Solid experience with Docker, CI/CD pipelines (e.g., GitHub Actions, Argo), and model registries.
• Leadership & Communication: Proven ability to lead small, highly technical teams and clearly communicate complex concepts to stakeholders.

Nice-to-Have Skills

• Experience with agentic workflows (e.g., AutoGen, CrewAI).
• Familiarity with multi-modal models (text, image, etc.).
• Knowledge of advanced LLM fine-tuning techniques (e.g., LoRA, QLoRA).
  • Strong SQL skills (especially with ClickHouse) and a keen eye for inference cost optimization.