AI Research Engineer (New York)

Description

The company builds AI agents that learn how a business's processes actually run and then carry out those operations. It is a Series A startup backed by Sequoia and other VC firms, led by co-founders who built and led Forward Deployed AI Engineering at Palantir. The team is growing in New York and London and is made up of engineers, AI researchers, and strategists.

The role is an AI Research Engineer based in New York.

Responsibilities

• Build and extend the core context-learning library, turning problems seen at customers into reusable platform features.
• Design and implement LLM-powered systems and agentic workflows from concept through to production.
• Build agents that edit, update, and maintain large knowledge bases on their own.
• Create continuous learning loops that use human corrections and production outcomes to spot knowledge gaps and changed procedures, and to improve prompts and instructions.
• Build reliability and confidence systems, including evaluation frameworks, confidence scoring, and logic that decides when to automate and when to hand off to a person.
• Architect async, scalable systems for complex AI orchestration.
• Help shape the company's AI strategy and product capabilities.
• Most of your time goes to the core context-learning library and the harness that runs the agents for every customer, covering continuous learning, context engineering, agent orchestration, and evaluation.
• The job mixes applied research with ownership of production systems: you find a failure, form a hypothesis, run the experiment, and ship the fix into live customer workflows.
• The system learns from a customer's existing material, such as knowledge base articles, support conversations, tickets, system logs, and agent traces, and turns it into step-by-step process instructions that people can inspect and agents can execute.

Requirements

• You have built a complex LLM system in production and can walk through the layers of engineering decisions, including what changed once real users arrived.
• You have practical depth in one or more of: context engineering, retrieval, agent orchestration, memory, evaluation, or learning from feedback.
• You can turn an unclear problem into a testable hypothesis, set a baseline, and separate real gains from noise.
• You enjoy open-ended problems where no known solution may exist yet.
• You move comfortably between research papers and production code.
• You communicate clearly with teammates and customers about your work.
• You have built LLM-based workflows that handle large request volumes, multi-agent systems in production, or evaluation frameworks for enterprise deployments.
• You bring intensity and self-direction to your work.
• You do not need to match every item above. The company welcomes people with different backgrounds and skill sets.

Conditions

Compensation is competitive: a base salary plus meaningful equity, in both New York and London.

Health, dental, and vision plans are offered. In the US, premium coverage is 100% and includes a One Medical membership. In the UK, private medical and dental cover is provided.

Paid time off is flexible.

The team works in person five days a week from the New York and London offices.

The company is an equal opportunity employer and does not discriminate on the basis of race, color, religion, sex, national origin, age, disability, genetic information, marital status, sexual orientation, gender identity, veteran status, or any other legally protected characteristic.

Benefits

• Lunch is provided in the office most days, along with snacks and drinks.
• A stipend covers setting up your workspace.