We're seeking a Senior AI Agent Engineer to design, build, and optimize agentic AI systems powered by large language models. You'll lead the development of autonomous, tool-using agents that can reason, plan, and execute complex workflows in real-world environments with high reliability and scalability.
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 systems that bring real impact to law and healthcare.
What You'll Do
- Design and implement autonomous AI agents and multi-agent systems for complex medical-legal workflows
- Build agentic architectures with planning, reasoning, memory, and tool-use capabilities (e.g., ReAct, function calling, orchestration frameworks)
- Develop LLM-powered pipelines using retrieval-augmented generation (RAG), vector search, and context management
- Create dynamic decision-making systems, including routing, task decomposition, and multi-step execution strategies
- Integrate agents with external APIs, databases, and proprietary data sources for tool-augmented intelligence
- Design evaluation frameworks, feedback loops, and guardrails to improve reliability, accuracy, and safety
- Optimize systems for latency, cost, and scalability in production environments
- Collaborate closely with product, engineering, and domain experts to translate real workflows into agent-driven systems
What We're Looking For
- 5+ years of experience in software engineering or AI/ML, with a strong focus on LLMs and agentic systems
- Hands-on experience building and deploying AI agents or LLM applications in production
- Deep understanding of prompt engineering, tool use, memory systems, and multi-step reasoning
- Experience with frameworks such as LangChain, LlamaIndex, or custom agent stacks
- Strong proficiency in Python and backend system design
- Familiarity with RAG, embeddings, and vector databases
- Strong problem-solving and system design skills with the ability to operate in ambiguous environments
- Experience in healthcare, legal tech, or other vertical AI applications is a plus
- Master's or Ph.D. in Computer Science, AI, or a related field is preferred
Why Join Us
- Build cutting-edge agentic AI systems that solve real, high-value problems
- Own core architecture and product direction in an early-stage, high-growth company
- Work at the intersection of AI, healthcare, and legal tech
- High-impact role with strong ownership and autonomy
- Competitive compensation, meaningful equity, and significant growth opportunities
Interview Process
All candidates will be required to demonstrate their technical capabilities through hands-on exercises and real-world problem solving during the interview process. This may include building or designing agentic systems, debugging workflows, or architecting solutions live. We maintain a highly selective hiring bar, with historically less than a 2% acceptance rate, as we are intentionally building a small team of exceptional engineers. This role is best suited for candidates who are confident in operating at the frontier of applied AI and delivering production-grade systems under high expectations. If you are confident in your abilities and up for the challenge, we strongly encourage you to apply.
