Senior AI Engineer – Agentic Systems & LLM Applications

Accountabilities:

• Design and implement autonomous agents and multi-agent orchestration systems capable of handling complex, open-ended tasks.


• Build and optimize production-grade applications on top of leading foundation models, with a focus on reliability, observability, scalability, and low-latency performance.


• Architect advanced Retrieval-Augmented Generation (RAG) pipelines and vector database strategies that provide agents with accurate, relevant, and real-time context.


• Develop sophisticated tool-calling, planning, reasoning, and autonomous execution workflows for AI agents.


• Contribute to AI-powered developer tools and internal frameworks that accelerate the development and deployment of AI-native products.


• Establish rigorous evaluation frameworks and Evals to measure model and agent performance in production environments.


• Implement monitoring, fine-tuning, testing, and optimization pipelines to improve accuracy, reliability, and safety.


• Collaborate across product and engineering functions to integrate foundation models into solutions that address real-world user needs.


• Help shape the technical architecture and engineering practices for scalable AI-native systems.


• Continuously evaluate emerging AI technologies, frameworks, and approaches and identify opportunities to incorporate them into production systems.

Requirements

• Proven experience building production applications using large language models, AI agents, or other advanced AI technologies, ideally within an AI-native startup, research environment, or developer-tool organization.


• Deep understanding of agentic systems, including agent frameworks, tool calling/function calling, autonomous planning, and reasoning loops.


• Expert-level proficiency in Python and/or TypeScript with Node.js.


• Hands-on experience with LangChain, LlamaIndex, or custom-built AI orchestration frameworks.


• Strong expertise with vector databases such as Pinecone, Weaviate, or Milvus.


• Experience designing efficient machine learning and data pipelines.


• Strong understanding of foundation model applications and the practical challenges of deploying LLM-powered systems at scale.


• Experience building sophisticated RAG architectures and retrieval strategies.


• Strong product intuition and the ability to translate emerging AI capabilities into useful, reliable products rather than purely academic experiments.


• Experience with production AI engineering practices, including evaluation, monitoring, optimization, and reliability.


• Ability to work effectively in a distributed, global-first environment with a high degree of autonomy and ownership.


• Strong problem-solving skills and a willingness to work on complex, ambiguous technical challenges.

• Fully remote opportunity with a global-first distributed team.


• Primary hiring regions include the United States, Europe, and India.


• Opportunity to work directly on autonomous agents, LLM applications, advanced RAG, and AI-native product infrastructure.


• Exposure to leading foundation models and modern AI development frameworks.


• Significant technical ownership at the intersection of product engineering and frontier AI research.


• Opportunity to build production-grade AI systems rather than experimental prototypes.


• For US-based candidates, a 3-month contractor-to-hire period followed by potential conversion to full-time employment.


• For candidates outside the US, long-term independent contractor engagement through OnTop.


• Opportunity to contribute to AI-powered developer tools and emerging AI technologies.


• Potential for significant career growth in a rapidly evolving AI environment.

Deze vacature komt van Lever. Originele vacature bekijken ↗