Staff Research Engineer — RRI Harness & AI Agents (Remote)

Sequen AI; United States; Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Unlimited PTO

Hybrid/Remote flexibility

World-class engineering culture

Job summary

Sequen AI is seeking a Staff Research Engineer to own the harness at the heart of the RRI system and contribute to applied research on how the agents operate. You will design experiments, ship reliable code, and extend evaluation infrastructure across long agent sessions in production settings.

You will work with Go and Python, ensuring systems are observable, resilient, and cost-aware, with strong ownership and cross-team collaboration.

Qualifications

• 7+ years of experience building production software.
• Experience with LLMs in agentic loops and tool calling.
• Debug across process, container, and network boundaries on Kubernetes and GPU nodes.
• Read a training script, understand a ranking metric, and discern signal from noise.
• Take absolute ownership for a system end to end, with focus on reliability.

Responsibilities

• Own the harness: Build and evolve the Python multi-agent runtime — orchestration, tool contracts, context and memory management, compaction, and model adapters across LLM providers.
• Contribute to applied research: Design and run experiments on how the agents work — prompting, tool design, context and memory strategies, and model choice.
• Build eval infrastructure: Deliver a fast, fixed eval set and a scorecard with measured noise bands that runs on every harness change.
• Engineer for resilience: Make multi-day sessions survive GPU failures, node replacement, rolling upgrades, provider errors, and credit limits.
• Deliver observability: Build event streams, cross-session analysis, per-agent cost and token accounting, and admin tooling over MCP.
• Cut waste: Find where agents idle, loop, or burn tokens, and fix it in code.
• Design clean contracts: Work with Go control plane and GPU proxy on interfaces between components.
• Support clients: Partner with applied scientists and forward-deployed engineers to diagnose production issues.

Skills

Production software

Agentic LLM

Kubernetes

ML fluency

Reliability ownership

Tools

Go

PyTorch

Job description

Sequen AI is seeking a Staff Research Engineer to own the harness at the heart of the RRI system and contribute to applied research on how the agents operate. You will design experiments, ship reliable code, and extend evaluation infrastructure across long agent sessions in production settings.

You will work with Go and Python, ensuring systems are observable, resilient, and cost-aware, with strong ownership and cross-team collaboration.