AI Engineer - AI Agents

Hatch
San Francisco
Workplace: HybridFull timeUSD 112,000 - 216,000 annuallyFunction: Data Science & Machine LearningSkills: ["Ownership","Bias for action","Mentorship","Communication","Cross-functional collaboration"]

Build and own systems powering voice and text AI agents, handling phone calls, SMS, and email conversations end to end. Design system-level prompts, implement reliable tool-calling integrations, and develop LLM-as-a-judge evaluations with AI observability to measure performance and prevent regressions. Partner with product and design while applying strong engineering practices (testing, CI/CD, feature flags, A/B experimentation) and mentoring junior engineers.

This position is no longer accepting applications.

  • See live roles at Hatch
  • Search all live jobs
  • Browse companies, collections, and locations hiring now
Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa

This position is no longer accepting applications.

See live roles at HatchSearch all live jobsBrowse companies, collections, and locations hiring now

Hatch
Hatch
2 days ago

AI Engineer - AI Agents

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 53 minutes agoStatus: Closed

Job Summary

Build and own systems powering voice and text AI agents, handling phone calls, SMS, and email conversations end to end. Design system-level prompts, implement reliable tool-calling integrations, and develop LLM-as-a-judge evaluations with AI observability to measure performance and prevent regressions. Partner with product and design while applying strong engineering practices (testing, CI/CD, feature flags, A/B experimentation) and mentoring junior engineers.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Design, build, and own systems powering Voice AI and Text AI agents across voice calls, SMS, and email conversations end to end.
  • •Craft system-level prompts that shape agent behavior, reliability, and outcomes based on real-world performance.
  • •Develop tool-calling integrations so agents can take safe, predictable actions such as booking, looking up customer data, and warm transfers.
  • •Build LLM-as-a-judge evaluations and AI observability (telemetry, traces, quality dashboards) to measure performance and catch regressions.
  • •Apply engineering practices (code review, automated testing, CI/CD, progressive delivery, feature flags, A/B experimentation, documentation) and mentor junior engineers.

Pay and Benefits

Salary: USD 112,000 - 216,000 annually
Perks:Health InsuranceDentalVisionPaid LeaveParental LeaveWellness Stipend401kEquityLearning BudgetRemote Work

Key Requirements

  • •Hands-on experience building with LLMs in production, including prompt engineering, tool/function calling, evaluation frameworks, or agent orchestration.
  • •Backend experience in Elixir, Go, or Python (or comparable server-side language) with ability to adapt as the stack evolves.
  • •Comfort working across the stack, from data model and LLM/agent logic to APIs and (when needed) UI.
  • •A track record of leading projects from spec to launch with multiple contributors.
  • •Clear communication skills and strong collaboration with technical and non-technical stakeholders.
Experience:AI agentsLLMsVoice AITool callingObservability
Skills:OwnershipBias for actionMentorshipCommunicationCross-functional collaboration
Tech Stack:ElixirPythonGoReactTypeScriptLLMPrompt engineeringTool callingFunction callingEvaluation frameworksAgent orchestrationObservabilityTelemetryTracesQuality dashboardsCI/CDFeature flagsA/B experimentationProgressive deliverySMS

Company Brief

Hatch
Hatch builds an AI-driven product intelligence platform that helps product teams discover insights, prioritize features, and generate user-facing content by analyzing product usage, feedback, and data to accelerate product decision-making and roadmapping.
Industry: SaaS
Website