AI Research Engineer

Remote (United States)

Job Details

Location: United States

Workplace: Remote

Experience: 5+ years of software engineering experience, including 1+ year applying Generative AI in production

Core Areas: Agentic AI Systems, Multi-Agent Architecture, Memory Engineering, LLM Evaluation, RAG, Vector Databases, Python, LangGraph

Compensation: $200,000 - $250,000 per year

About the Role

This opportunity is for an AI Research Engineer responsible for designing, building, and deploying next-generation agentic AI systems that bridge cutting-edge research with production-ready software. The role focuses on developing advanced reasoning agents, memory architectures, evaluation frameworks, and scalable AI systems that continuously improve performance in real-world environments.

The position combines applied AI research with production engineering, emphasizing agent architecture, context and harness engineering, retrieval systems, evaluation pipelines, and long-term AI reliability. You will work closely with engineering and product teams to transform emerging research into production-grade AI capabilities.

What You'll Do

Agentic Architecture

• Design and implement advanced multi-step reasoning agents that support tool use, planning, reflection, and self-improvement loops.
• Develop frameworks for multi-agent coordination and task decomposition.
• Improve the reliability, latency, and cost efficiency of AI agent execution.

Memory Systems

• Architect short-term and long-term memory systems, including episodic, semantic, retrieval-based, and hybrid memory approaches.
• Build context compression, retrieval, and grounding mechanisms for AI agents.
• Explore continual learning strategies and persistent state management techniques.

Evaluation & Reliability

• Design and implement evaluation frameworks that measure task success, reasoning quality, robustness, and overall agent performance.
• Develop automated evaluation pipelines using synthetic datasets, adversarial testing, and regression testing.
• Establish production metrics and benchmarking systems that improve long-term agent reliability.

Research to Production

• Translate emerging AI research into scalable production systems.
• Design experiments, analyze results, and rapidly iterate on production AI capabilities.
• Contribute to internal technical direction and knowledge sharing across engineering teams.

Qualifications

Required Experience

• 5+ years of software engineering experience, including at least 1 year applying Generative AI in production environments.
• Proven experience building or researching agent frameworks, tool-using LLM systems, and memory or retrieval architectures.
• Experience designing and deploying production AI systems that bridge research and real-world applications.
• Experience following emerging AI research and validating new techniques through production deployment.

Required Skills

• Expert-level Python development.
• Strong experience with Retrieval-Augmented Generation (RAG), vector databases, and hybrid retrieval systems.
• Deep understanding of context engineering and harness engineering for large language models.
• Experience working with OpenClaw and Claude Code harness architectures.
• Strong knowledge of multi-step reasoning agents, tool-using LLMs, and memory systems.
• Ability to improve consistency and reliability of non-deterministic LLM outputs.
• Strong ownership mindset with the ability to independently solve ambiguous technical challenges.
• Experience operating effectively within early-stage startup environments.

Preferred Qualifications

• Experience with agent orchestration frameworks such as LangGraph, AutoGen, or custom orchestration systems.
• Experience implementing AI safety guardrails, hallucination mitigation, and structured output enforcement.
• Experience designing offline and online LLM evaluation frameworks using synthetic data and human-in-the-loop evaluation.
• Publications or open-source contributions related to applied AI.
• Experience applying advanced context and harness engineering techniques to customer-facing AI products.
• Founder experience, early-stage startup experience, or experience launching new AI technologies within an established organization.

Benefits

• Company-paid health insurance.
• 401(k) plan with employer matching.
• Self-managed paid time off.
• Parental leave.
• Additional employee benefits.
• 100% remote work environment with company-provided equipment.
• Semi-frequent local and national travel, including occasional overnight travel.