Senior Agent Harness Engineer

Savvy

Where
NYC Office
Pay
$200 an hour
Type
Full time

Posted 8 days ago· Checked live at Savvy 1 hour ago

Live.Open on the employer's own site.

See how you score for this job

One sentence and your resume. We score it against what Savvy asks for, line by line.

See my score
Is this job still open?
Yes. We checked it live on Savvy's own hiring page 1 hour ago.
What is the job?
Wealth management is a $545 billion industry that still runs on manual work. 75% of advisors offer no digital communication beyond email, and most still build financial plans by hand in Excel. Savvy is reinventing what it looks like to be a financial advisor.
What does it pay?
$200 an hour, as the posting states.
Our verdict
Live. Open on the employer's own site.

What the job is

Wealth management is a $545 billion industry that still runs on manual work. 75% of advisors offer no digital communication beyond email, and most still build financial plans by hand in Excel. Savvy is reinventing what it looks like to be a financial advisor.

What you'll do

  • Own developer and agent experience: Set the roadmap for how our engineers and coding agents navigate the codebase, use internal tools, run tests, review changes, and ship software.
  • Build the cloud coding experience: Build the developer-facing layer around our existing compute foundations, including task intake, environment setup, context, tools, permissions, observability, review, and delivery.
  • Improve agent output at the source: Change repository structure, interfaces, documentation, instructions, and feedback loops so agents produce correct code and sound architecture more consistently.
  • Engineer context deliberately: Design what agents receive up front, discover progressively, persist, compact, hand off, or discard. Choose models and reasoning effort based on evidence from the job, not habit.
  • Own our internal skills system: Raise the quality of our shared skills and instructions through clear contribution standards, evaluation, discoverability, progressive disclosure, maintenance, and pruning.
  • Fix everyday developer friction: Improve CI speed and reliability, local setup, testing, debugging, deploy workflows, and the other bottlenecks that cost engineers time.
  • Measure what works: Combine developer research and satisfaction data with DORA or SPACE measures and task-level agent evaluations. Inspect traces, establish baselines, and test whether changes improve correctness, reviewability, cost, latency, and human intervention.
  • Drive adoption: Work directly with engineers, teach effective practices, and turn successful experiments into defaults. When the root problem is the codebase or engineering process, make that case and help fix it.
  • Partner on safe autonomy: Work with our infrastructure and security engineers on sandboxing, credentials, approvals, auditability, and the controls needed to give cloud agents useful access without giving them unlimited access.

What we're looking for

  • Exceptional with coding agents: You use Claude Code, Codex, Cursor, or similar tools for substantial work and can show how you decompose tasks, manage context, choose models, inspect failures, and consistently produce maintainable software. Faster output alone is not the bar.
  • Internal tools with real users: You have built developer tooling or a platform that engineers beyond your immediate team relied on. You learned from their behavior and support burden, not only from what they said they wanted.
  • CI or large-codebase experience: You have made a meaningful improvement to CI, testing, repository workflows, or developer productivity in a substantial, long-lived codebase.
  • Product judgment for internal systems: You can interview developers, separate symptoms from root causes, turn evidence into a roadmap, and say no to attractive work that will not improve the system.
  • Strong software engineering: You have built and operated substantial production software. We are open on language and framework, but you must be able to move from diagnosis to a durable implementation yourself.
  • Evaluation over intuition: You know that agent behavior is nondeterministic and changing quickly. You compare prompts, context, tools, models, and workflows against representative tasks rather than declaring success from a demo.
  • Cross-team influence: You can set standards and change defaults across teams without becoming a gatekeeper. You explain the evidence, earn trust, and remain accountable for the experience you create.
  • Pragmatic range: You are comfortable moving between platform code, repository conventions, evaluation data, developer interviews, documentation, and hands-on enablement. This is not a prompt-writing, DevRel, or framework-only role.

Nice to have

  • Experience building cloud or remote development environments, coding-agent control planes, or secure execution sandboxes.
  • Experience building or operating an agentic code review system.
  • Experience designing agent tools, skills, context systems, memory, orchestration, or model-routing infrastructure.
  • Experience using DORA, SPACE, or similar frameworks without reducing developer productivity to a single metric.
  • Experience in financial services or another security- and compliance-sensitive environment.

Benefits

  • Competitive salary and equity package
  • We offer a generous relocation package to help top talent make the move to our NYC office
  • Unlimited PTO + paid company holidays
  • Access to holistic medical, dental, and vision plans
  • Company 401(k) (including Mega backdoor Roth options), Commuter, and HSA/FSA plans
  • NYC office in Union Square
  • Lunch and snacks provided in the office, & dinner if you stay late
  • Access to virtual mental health care (Spring Health) and health concierge (Rightway) to help you find the right care
  • Access to counseling for stress management, dependent care, nutrition, fitness, legal, and financial issues (Guardian WorkLifeMatters EAP)
  • Benefits are available to full-time employees

Similar open jobs

Jobs in New York (19157)