We’re seeking an Applied AI Scientist to design, develop, and optimize intelligent agent systems powered by large language models. You’ll drive research and engineering to deliver high-impact, real-world AI solutions that are reliable, scalable, and transformative.

About Us

Superinsight.ai is one of the fastest-growing startups in the legal and medical sectors in the U.S. We're redefining how attorneys interact with medical records using AI to accelerate and improve the way legal professionals process injury and disability claims. As a venture-backed company and proud member of the NVIDIA Inception Startup Program, we’re building secure and scalable tools to bring real impact to law and healthcare.

What You’ll Do

• Research and implement AI agents and multi-agent architectures, including agentic workflows, orchestration frameworks, and tool-use integration.
• Develop dynamic reasoning and interaction strategies, leveraging chain-of-thought reasoning, decision policies, and routing mechanisms.
• Build and optimize LLM-based pipelines with retrieval-augmented generation (RAG), vector search, context management, and grounding to external data.
• Apply few-shot learning, in-context learning, and post-training optimization, including instruction tuning, prompt engineering, and fine-tuning (SFT, LoRA).
• Leverage reinforcement learning to improve agent decision-making, coordination, and RLHF pipelines.
• Integrate agents with external APIs and tools for advanced tool-augmented workflows.
• Design evaluation pipelines and feedback loops to continuously improve agent performance, reliability, and factuality.
• Lead projects like agentic search, due diligence pipelines, token recommendation systems, and generative response optimization.

What We’re Looking For

• Master’s degree in CS, AI, Data Science, or related field (PhD preferred).
• 3+ years of experience in AI/ML system design, especially NLP and deep learning.
• Expertise with LLMs, prompt engineering, few-shot/in-context learning, and post-training techniques.
• Hands-on experience with reinforcement learning applied to AI agents.
• Strong proficiency in Python and frameworks such as PyTorch, TensorFlow, Hugging Face, or LangChain.
• Familiarity with information retrieval, vector search, and knowledge integration.
• Proven ability to build scalable, high-performance AI solutions.
• Collaborative mindset to work across research, engineering, and product teams.

Why Join Us

• Lead innovation at the intersection of AI, legal tech, and healthcare.
• Work on projects that directly improve outcomes for real people.
• Remote-first culture emphasizing trust, ownership, and speed.
• Competitive salary, meaningful equity, and growth opportunities for your career.