Senior Applied AI Engineer, AI Platform

Bunch
Portugal
Workplace: RemoteFull timeFunction: Data Science & Machine LearningSkills: ["Ownership","Collaboration","Platform mindset","Pragmatism","Quality standards"]

Build and ship AI agents that automate fund-operations workflows, from prototype to production, and keep them reliable through evaluation, regression suites, and human review. Own the end-to-end AI application architecture—orchestration, multi-agent design, RAG/MCP, guardrails, and human-in-the-loop controls for investor-money workflows. Run versioned rollouts with observability, failover, and rate-limited provider fallback within EU data residency, and establish platform patterns other teams reuse.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Bunch
Bunch
2 days ago

Senior Applied AI Engineer, AI Platform

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 7 hours agoStatus: Live

Job Summary

Build and ship AI agents that automate fund-operations workflows, from prototype to production, and keep them reliable through evaluation, regression suites, and human review. Own the end-to-end AI application architecture—orchestration, multi-agent design, RAG/MCP, guardrails, and human-in-the-loop controls for investor-money workflows. Run versioned rollouts with observability, failover, and rate-limited provider fallback within EU data residency, and establish platform patterns other teams reuse.
Location: Portugal
Workplace: Remote
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Design and build agents that automate real fund-operations workflows, integrating with services, data model, and authorization system from prototype through production and after.
  • •Create and continuously improve the evaluation layer using real-document test cases, CI regression suites, human review, and measurable success criteria (accuracy, latency, cost).
  • •Own AI application architecture including orchestration and multi-agent design, tool contracts, memory, and context engineering (RAG, MCP) with guardrails and human-in-the-loop controls.
  • •Operate AI in production with versioned, feature-flagged rollouts, provider fallback, regional failover within EU data residency, and observability to trace and fix failures.
  • •Turn agent capabilities into a platform by documenting patterns and partnering with DevX while mentoring engineers across teams on agent and LLM practice.

Pay and Benefits

Perks:Remote WorkPaid Leave

Key Requirements

  • •5+ years building production software, including owning an agent or LLM-powered capability end to end once it was live.
  • •Deep experience in orchestration and context engineering (tool contracts, memory, RAG, multi-agent design) with Mastra, ai-sdk, LangGraph or similar; integrate agents into a real product and authorization model.
  • •Ability to evaluate non-deterministic systems with test cases from real documents, regression suites in CI, human review, and clear success criteria focused on accuracy, latency, and cost.
  • •Strong production ownership: diagnose failures from traces, tune cost/latency, and handle provider rate limits and fallback reliably.
  • •Backend experience with TypeScript and/or Python.
Experience:FintechPrivate marketsRegulatedLLM-powered systems
Skills:OwnershipCollaborationPlatform mindsetPragmatismQuality standards
Tech Stack:MastraAi-sdkLangGraphTypeScriptPythonSvelteReactNode.jsNest.jsMySQLPostgreSQLVercel ai-sdkGoogle VertexGeminiAWS BedrockKubernetesDatadogFusionAuthRetoolMCP

Company Brief

Bunch
bunch builds an end-to-end operating system for private markets, digitizing fund and entity creation, investor onboarding, and portfolio operations to streamline fund administration for VCs, PE and alternative asset managers.
Industry: Fintech Infrastructure
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Valuation: USD 50M to 100M
Funding: Series A
Headquarters: Berlin, Germany
Founded: 2021
Glassdoor
Glassdoor: 4.0
WebsiteLinkedInGlassdoor