Remote job
Research & Development Engineer
Job details
About this role
Role overview
Investigate and improve systems that translate software engineering tasks into changes people can review. You’ll combine applied research, prototyping, and careful measurement to determine which agent workflows work reliably in practice and how they can become maintainable product capabilities.
Responsibilities
- Explore methods for agent planning, code understanding, tool use, and verification. - Build prototypes and evaluation harnesses using representative software tasks. - Analyze failure modes and assess whether benchmark improvements translate to practical gains. - Compare model and workflow choices for quality, latency, and cost. - Work with product engineers to carry validated approaches into maintainable implementations. - Document experiments, limitations, and results so others can reproduce them.
Requirements
- Strong programming skills and experience implementing data-driven experiments. - Familiarity with LLMs, agent workflows, machine learning, or program analysis. - Ability to design meaningful evaluations and interpret noisy results carefully. - Solid grounding in software development, testing, and debugging. - Comfortable reading research papers and turning ideas into practical prototypes. - Clear technical writing and ability to work independently on uncertain problems.
Nice to have
- Research publications, open-source research tools, or substantial independent projects. - Experience evaluating coding agents, retrieval systems, or test generation. - Applied work on model reliability, security, or inference efficiency.
Benefits and work setup
This is a remote position. Hiring locations, working-hour overlap, and engagement terms are discussed during the hiring process. Early priorities include establishing a reproducible baseline, measuring a significant failure mode, and delivering an evaluated prototype with a recommendation for next steps.