Sequen
Staff Research Engineer – RRI Harness
$300K–$350K
United States · Remote · Staff · Full-time · Posted Oct 9, 2026
- Experience
- 7+ years building production software.
About the job
Own and improve Sequen’s Python multi-agent runtime, run applied experiments on agent behavior, and build evaluation and reliability infrastructure for long-running AI research sessions.
What you'll do
- Build and evolve the harness, including orchestration, tool contracts, context and memory management, compaction, and model adapters.
- Run experiments on prompting, tool design, context and memory strategies, and model choice; ship changes that improve results.
- Build evaluation, resilience, observability, and cost-accounting systems, and help diagnose client production issues.
What they ask for
- 7+ years building production software, with strong Python and experience with distributed or long-running systems.
- Experience building with LLMs in agentic loops, including tool calling, prompt and context management, streaming, and retries.
- Ability to debug across process, container, and network boundaries on Kubernetes and GPU nodes.
- ML fluency, including reading training scripts and interpreting ranking metrics and regression noise.
Nice to have
- Applied ML or LLM research and evaluation infrastructure experience.
- Working knowledge of Go, customer-controlled deployments, ML platforms, or open-source agent and evaluation tooling.
Pay
$300K – $350K (base salary)
Tools
Python, Go, Kubernetes, GPU, MCP, PyTorch
AI focus
Applied research and engineering for autonomous, long-running AI agents: testing agent behavior and improving prompting, tool use, context and memory strategies, model choice, and evaluation.
Model-written summary · the original posting is authoritative