Software Engineer, Sandbox & Agent Executor

Retool
San Francisco
Workplace: HybridFull timeUSD 163,800 - 306,000 annuallyFunction: Software EngineeringExperience: 6+ yearsSkills: ["Systems thinking","Curiosity","Mentoring","Measurement","Debugging non-determinism"]

Build and own the agent platform powering AI features, shaping model-driven behavior across product, infrastructure, and evaluation layers. Design prompting, context, retrieval, routing, and tool-use strategies for long-horizon workflows, and create evaluation systems to prevent regressions under non-determinism. Diagnose issues like hallucinations and instruction drift using transcripts and traces, partnering with product and infrastructure to provision and roll out agent workloads in cloud and self-hosted environments.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Retool
Retool
2 days ago

Software Engineer, Sandbox & Agent Executor

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 5 hours agoStatus: Live

Job Summary

Build and own the agent platform powering AI features, shaping model-driven behavior across product, infrastructure, and evaluation layers. Design prompting, context, retrieval, routing, and tool-use strategies for long-horizon workflows, and create evaluation systems to prevent regressions under non-determinism. Diagnose issues like hallucinations and instruction drift using transcripts and traces, partnering with product and infrastructure to provision and roll out agent workloads in cloud and self-hosted environments.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Own agent behavior across multiple product surfaces, including quality, safety, variance, and failure modes.
  • •Work across product and infrastructure to shape agent behavior, understand runtime costs, and support agent workloads as the infrastructure team counterpart.
  • •Design and evolve prompting, context construction, retrieval, routing, and tool-use strategies for long-horizon workflows, and build statistical evaluation systems.
  • •Detect, diagnose, and resolve non-deterministic failures (e.g., hallucinations, partial correctness, instruction drift) using transcripts and traces.
  • •Partner with product and infrastructure teams to provision, isolate, and roll out agent workloads for cloud and self-hosted customers.

Pay and Benefits

Salary: USD 163,800 - 306,000 annually
Equity and Bonus:Equity
Perks:Health InsuranceDentalVision401k

Key Requirements

  • •6+ years of professional engineering experience with ownership over complex production systems.
  • •Production experience with agentic systems, including context engineering, tool use, and evaluation frameworks at real user scale.
  • •Hands-on experience sandboxing technology to run agents inside sandboxed environments.
  • •Experience with Kubernetes (or equivalent), owning services end to end (e.g., EKS, ECS).
  • •Ability to think in systems, measure probabilistic correctness, and mentor engineers on when to use a model vs. not.
Experience:6+ yearsAgentic systemsCloudSelf-hostedEnterprise
Skills:Systems thinkingCuriosityMentoringMeasurementDebugging non-determinism
Tech Stack:TypeScriptNode.jsReactKubernetesEKSECS

Company Brief

Retool
Provides a low-code platform for building internal tools and business applications, enabling developers and teams to assemble UIs on top of databases and APIs to accelerate operational workflows.
Industry: Developer Tools
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series D
Headquarters: San Francisco, United States
Founded: 2017
WebsiteLinkedIn