Senior AI Engineer – Agentic Systems & LLM Applications

We are building the next generation of AI-native products, moving beyond simple chat interfaces into the realm of autonomous agents and advanced foundation model applications. We are looking for an AI Engineer who operates at the intersection of product engineering and frontier AI research to design, build, and scale our agentic infrastructure. As a core member of our AI team, you will be responsible for crafting the systems that allow LLMs to reason, act, and solve complex, non-deterministic workflows in production environments. Key Responsibilities Agentic Systems Development: Design and implement autonomous agents and multi-agent orchestration frameworks to handle complex, open-ended tasks. LLM Infrastructure: Build and optimize robust applications on top of foundation models (GPT-4, Claude 3.5, Gemini, etc.), focusing on reliability, observability, and low-latency performance. Advanced RAG & Retrieval: Architect sophisticated Retrieval-Augmented Generation (RAG) pipelines and vector database strategies to provide agents with high-fidelity, real-time context. Developer Tooling: Contribute to the creation of AI-powered developer tools and internal frameworks that accelerate our AI-native product development cycle. Production-Grade AI: Move beyond "demo-ware" by implementing rigorous evaluation frameworks (Evals), monitoring, and fine-tuning pipelines to ensure production-level accuracy and safety. Technical Profile & Experience We are seeking engineers who have been in the "trenches" of the AI-native revolution. Ideally, you possess: Frontier AI Experience: A proven track record of building applications on LLMs or AI agents within startups or research labs (e.g., Anthropic, OpenAI, DeepMind, LangChain, or AI-native dev-tool companies). Agentic Reasoning: Deep understanding of agent frameworks, tool-calling (function calling), and autonomous planning/reasoning loops. Modern AI Stack: Languages: Expert-level proficiency in Python and/or TypeScript (Node.js). Orchestration: Hands-on experience with LangChain, LlamaIndex, or custom-built orchestration layers. Data: Expertise in Vector Databases (Pinecone, Weaviate, Milvus) and building efficient ML/Data pipelines. Product Intuition: The ability to integrate foundation models into real-world products that solve tangible user problems, rather than just academic experiments. Location & Logistics Global Remote: We are a distributed team with a global-first mindset. Primary Regions: United States, Europe, and India. Employment Model: Outside the US: Long-term engagement as an Independent Contractor via OnTop. Inside the US: Hybrid model (3-month Contractor-to-Hire period followed by conversion to Full-Time Employment/FTE). Join Us Submit your CV and embark on this exciting journey that could be a life-changing career move! Best regards, T-mapp Team