Job
Description
About Sentient Sentient Foundation is building the cognitive layer of the decentralized web creating open, composable, agent-based AI systems that serve humanity, not platforms. Our flagship product, Sentient Chat , is a generative AI assistant powered by open-source models and governed by its users. We operate at the frontier of AI, Web3, and open innovation. The Role We re looking for a Senior AI Engineer with a strong foundation in backend development and a proven track record of shipping real-world GenAI systems. You ll work at the heart of Sentient s AI stack designing, deploying, and iterating on intelligent agents, RAG pipelines, and LLM-powered features in production. This is a role for someone who thrives in 0 1 environments, loves working with state-of-the-art AI frameworks, and wants to help shape the future of decentralized intelligence. What You ll Do Design, build, and scale production-grade GenAI agents Work with LLM frameworks , agentic systems , RAG pipelines , and eval tooling Build backend services and APIs that power Sentient Chat and future AI-native products Collaborate with researchers, infra engineers, and product teams to ship iteratively and intelligently Help define best practices for prompt engineering , model selection , and continuous evaluation Stay close to the bleeding edge of AI, testing and integrating advances quickly What We re Looking For 5-10 years of backend software engineering experience (Python, Node.js, Go, or similar) 2-4 years working directly with Generative AI systems (LLMs, diffusion models, or agents) Proven experience with: Agentic frameworks (LangChain, AutoGen, CrewAI, etc.) Retrieval-augmented generation (RAG) and semantic search Prompt design , task decomposition , and evaluation pipelines Understanding of scalable infrastructure and deploying AI in production Bonus: experience with model training , fine-tuning , or hosting open-source LLMs (vLLM, LoRA, etc.) A builder s mindset curious, fast-moving, and unafraid of ambiguity
