Work Across
Get started
All jobs
Save

Senior Applied AI Engineer, AI Platform (f/m/d)

bunch
Contract type
Ongoing
Work mode
Hybrid · 3 days/week in office · Berlin, Germany
Experience
Senior · 5+ years

Job description

Senior Applied AI Engineer on the AI Platform team at bunch, taking AI from working to relied upon by building and shipping agents that automate fund-operations workflows, with evaluation, architecture and production ownership.

At a glance

Employment
Full-time
Work mode
Hybrid · 3 days/week in office · Berlin, Germany
Languages
English

What you'll do

  • Build and ship agents that automate real fund-operations workflows, owning them from prototype through production and after, integrated with services, data model and authorization system
  • Build the evaluation layer: test cases from real documents with expected output, regression suites in CI, human review where correctness is non-negotiable, and clear success criteria for agents completing complex tasks end to end
  • Improve accuracy, latency and cost of agents
  • Own the AI application architecture: orchestration and multi-agent design, tool contracts, memory, and context engineering (RAG, MCP) with clear domain boundaries, plus guardrails, approvals and human-in-the-loop controls
  • Run agents in production: versioned, feature-flagged rollout of agent versions; rate limits, provider fallback and regional failover within EU data residency; observability to trace failures across services
  • Make it a platform: consolidate document parsing and extraction into the team, make shared evaluation and observability consumable by other teams, set patterns other engineers inherit, partner with DevX and mentor engineers on agent and LLM practice
  • Review the MCP offering end to end and ship it to the first customers with access boundaries, evaluation and observability
  • Stand up shared observability for AI workloads (token usage, estimated cost, latency, failures and retries per provider) on a dashboard
  • Publish v1 of agent patterns (domain boundaries, tool contracts, prompt and eval conventions), reviewed with DevX and adopted by at least one team outside AI Platform

What we're looking for

  • 5+ years building production software, including at least one agent or LLM-powered capability taken end to end and still owned once live
  • Real depth in orchestration and context engineering — tool contracts, memory, RAG, multi-agent design — with Mastra, ai-sdk, LangGraph or similar; integrated agents into a real product and its authorization model
  • Evaluation: making a non-deterministic system measurable, from test cases built on real data to regression suites and human review
  • Production ownership: reading traces, diagnosing failure modes, tuning cost and latency, handling provider rate limits and fallback
  • Backend experience with TypeScript and/or Python
  • Platform mindset: building for other engineers as much as for end users, with standards adopted through trust
  • Pragmatic: starting from the business outcome, choosing deterministic solutions when right, knowing when good enough is good enough

Nice to have

  • Experience in fintech, private markets, or another regulated, document-heavy domain
  • Working under EU data-residency constraints

Your team

AI Platform

Team that runs AI in production at bunch, including a live document extraction pipeline in fund operations, agent workflows on Mastra, evaluations, and multi-provider fallback inside EU data residency.

Benefits

  • Customizable benefits package (wellbeing, sport, mobility, food, and more)
  • 28 days of vacation, plus 2 company days and local public holidays
  • Hybrid setup (3 days/week in office)
  • Up to 6 remote calendar weeks a year
  • A great tech and work setup
  • Work with a diverse team of 130+ bunchies from 40+ countries, with leaders who are best-in-class in their domains

How to get hired

  1. 1People Team Interview (30 min)
  2. 2Hiring Manager Interview (60 min)
  3. 3Technical Interviews (2 x 60 min)
  4. 4Final Round with CTO Leandro (45 min)

Apply

Save

About bunch

Building the backbone of private markets

bunch combines AI-powered automation with deep regulatory expertise to replace fragmented spreadsheets and manual processes with one integrated platform across the fund lifecycle, purpose-built for private markets.

Mission

Building the operating infrastructure for the next generation of private markets, combining AI-powered automation with deep regulatory expertise.

Key facts

  • 130+ bunchies
  • Private markets fund operations infrastructure
  • 4x ARR in 2025
  • Crossed 150 fund managers and 12,000 LPs on the platform
  • Closed $35M Series B in May 2026
  • Team of 130+ bunchies from 40+ countries
  • Private markets heading toward $32 trillion in Assets Under Management

What they value

  • Ownership
  • Growth through real responsibility
  • Thoughtful, ambitious team
  • Inclusive environment where diversity is valued and celebrated