Senior AI Engineer

Senior AI Engineer

We are seeking a highly skilled and motivated Senior AI Engineer to lead the development and deployment of our next-generation LLM-powered services. The ideal candidate will possess a deep understanding of prompt orchestration, scalable software architecture, and cloud infrastructure, with a commitment to high-quality, performant, and maintainable code.

Core Responsibilities

• Design, develop, and deploy high-performance, low-latency AI services, primarily utilizing Large Language Models (LLMs).
• Architect and implement robust prompt orchestration workflows using advanced tools (e.g., LangGraph, Flowise, or equivalent framework), ensuring exceptional quality and detailed control over model interactions.
• Build and maintain scalable software solutions, primarily focusing on microservices architecture with a strong emphasis on performance optimization for LLM inference.
• Establish and enforce software engineering best practices, including clean code principles, design patterns, and comprehensive observability (logging, tracing, metrics).

Required Skills & Experience

1. AI & Machine Learning Expertise

• Advanced Prompt Engineering: Proven experience in designing, testing, and managing complex prompt chains and workflows for various LLM applications.
• LLM Ecosystem Knowledge: Solid understanding of different model types (e.g., LLMs, embedding models, cross-encoder rerankers), their respective use cases, and best practices for model evaluation and testing.
• AI-Powered Development: Experience leveraging AI-enhanced development tools, such as Amazon Q, GitHub Copilot, or similar IDE assistants, to increase productivity.

2. Software & Data Engineering

• Strong Software Engineering Fundamentals: Expert proficiency in a major programming language (e.g., Python, Go) and demonstrated ability to build high-quality, production-ready code.
• Data & Database Proficiency: Excellent command of SQL with the ability to understand complex database schemas and write efficient, complex queries.
• Vector Database Experience: Practical experience with Vector Databases (e.g., Pinecone, Weaviate, Milvus, Qdrant) and their application in Retrieval-Augmented Generation (RAG) systems.

3. Cloud & Infrastructure

• Cloud Services (AWS Focus): Strong foundational knowledge and hands-on experience with AWS cloud services, particularly those relevant to deploying and scaling AI/ML workloads.
• Data Infrastructure: Conceptual understanding of data warehousing solutions and best practices for managing data used in production AI systems.

4. Quality & Operational Excellence

• Quality-Driven Development: A proven track record of delivering high-quality solutions, with a deep understanding of various testing methodologies (unit, integration, end-to-end) and CI/CD practices.

5. Security & Architecture

• Multi-Tenancy Expertise: Strong understanding and practical experience in designing and implementing multi-tenant architectures, ensuring strict isolation and security across client data and services.
• Data Protection & Compliance: Deep knowledge of OWASP security principles and hands-on experience implementing data masking, PII (Personally Identifiable Information) removal, and data governance in AI systems to ensure compliance and privacy.