Production AI Engineer: Build LLM Apps & AI Pipelines
Posted Updated
Description
Codextra Labs is hiring an AI Engineer to design, build, and deploy production-ready AI products using LLMs, retrieval systems, and automation. You’ll work across the development lifecycle, turning ideas into reliable software and shipping AI-powered services in a modern cloud stack.
Strong Python, API, and backend fundamentals are essential for success. You’ll develop RAG systems, tools, and workflows, evaluate latency and cost, and implement robust monitoring and fallbacks.
Design, build, and maintain AI-powered applications and backend services. Build LLM applications, including RAG systems using embeddings, vector search, retrieval, and reranking. Develop AI agents and workflows that use tools, APIs, and external data sources. Build APIs and data pipelines that support AI applications. Work with structured and unstructured data from documents, databases, APIs, and other sources. Experiment with models, prompts, retrieval strategies, and system architectures. Evaluate systems for accuracy, latency, reliability, and cost. Add validation, error handling, fallbacks, monitoring, and other safeguards needed for production systems. Deploy, monitor, debug, and improve AI services based on real-world usage. Strong Python skills and backend experience. APIs, testing, debugging, version control, and solid architecture fundamentals. Experience with REST APIs, JSON, databases, and backend development. Familiarity with LLM concepts, embedding, vector search, and RAG is a plus. Competitive compensation Flexible working arrangements Opportunity to build real AI productsSkills
Sign in to read and join the discussion.