AI Engineering
Responsibilities:
• Model Deployment & Integration: Seamlessly wrap machine learning, deep learning, and generative AI models into high-performance, production-ready APIs and microservices.
• LLM Orchestration & Engineering: Design and optimize complex prompt engineering workflows, implementation of Retrieval-Augmented Generation (RAG) frameworks, and multi-agent systems using LangChain or LlamaIndex.
• Data & Inference Pipeline Development: Architect and maintain scalable backend data pipelines to handle real-time preprocessing, model inference, and efficient post-processing.
• MLOps & Infrastructure Automation: Establish automated CI/CD pipelines for model testing, version control (Git), deployment, and continuous production monitoring.
• Performance Tuning & Optimization: Optimize model latency, memory footprint, and compute costs through techniques such as model quantization, caching, and infrastructure scaling.
• Cross-Functional Collaboration: Partner with backend engineers, frontend developers, and product teams to translate advanced AI features into seamless, user-facing application capabilities.
Preferred Skills/Requirements:
• Software Engineering Excellence: Deep proficiency in Python alongside a strong grasp of software architecture, clean code practices, and building robust RESTful or gRPC APIs (e.g., FastAPI).
• AI & Machine Learning Frameworks: Core competence with machine learning libraries and modern AI ecosystems (e.g., PyTorch, Hugging Face, Scikit-Learn) and direct integration with foundational model APIs (OpenAI, Anthropic).
• Advanced LLM & RAG Architectures: Practical experience building production-grade Retrieval-Augmented Generation (RAG) systems and working with vector databases (e.g., Pinecone, Qdrant, Chroma) for semantic search.
• Cloud & Containerization Infrastructure: Solid experience deploying applications to cloud environments (Azure, AWS, or GCP) paired with a strong mastery of containerization tools like Docker.
• Inference Optimization & MLOps: Knowledge of model serving optimizations (e.g., vLLM, quantization) and setting up automated CI/CD pipelines for model versioning and monitoring.
• AI Governance & Security: A strong understanding of secure LLM engineering, including protecting against prompt injections and implementing data privacy compliance standards.