AI Automation Engineer

One Peak Partners LLP; Kraków; Hybrid; PLN 90,000 - 150,000; Full time

Benefits offered by this job

Health and life insurance

Office in Krakow city centre

Employee benefits

Learning & development budget

Job summary

Keepit is seeking a Mid-Level AI Automation Engineer to design, build, and operate AI-driven automations and agents supporting GTM and Finance. You will work hands-on with Claude Desktop, Claude API, MCP integrations, and local/hosted LLMs to transform manual workflows into reliable, monitored agent systems.

This builder role provides end-to-end ownership—from prototyping an agent to production hardening for GTM, Sales, Marketing, and Finance teams, emphasizing security and scalability.

Qualifications

• Hands-on experience building AI automations/agents with Claude Desktop and Claude API.
• Domain experience with GTM (Sales/Marketing/RevOps) and Finance use cases.
• Proficient in Python; familiarity with TypeScript/JavaScript and Bash.
• Experience with MCP servers or MCP gateway deployments.
• Practical experience deploying local/self-hosted LLMs and RAG pipelines.

Responsibilities

• Design, build, and deploy AI automations and agents using Claude Desktop and Claude API.
• Partner with GTM and Finance stakeholders to identify automation opportunities.
• Develop and maintain MCP servers/gateways for secure integrations.
• Stand up local LLM environments and RAG pipelines for privacy and latency needs.
• Build an agent harness around models (orchestration, tooling, memory, guardrails).
• Write production‑quality Python and other languages for tooling and data pipelines.
• Establish testing, monitoring, and evaluation for reliability and cost.

Skills

Claude Desktop

Claude API

MCP

Local LLMs

RAG pipelines

Python

TypeScript

Agent development

Tools

Docker

Job description

Keepit is looking for a Mid-Level AI Automation Engineer to design, build, and operate AI-driven automations and agents that support our Go-To-Market (GTM) and Finance functions. You will work hands‑on with the Claude Desktop application and API, local and hosted LLMs, and Model Context Protocol (MCP) integrations to turn manual, repetitive workflows into reliable, monitored agentic systems. This is a builder role: you will own solutions end-to-end, from prototyping an agent to hardening it for production use by GTM Systems, Sales, Marketing, and Finance teams.

You will:

• Design, build, and deploy AI automations and agents using Claude Desktop and the Claude API for real business workflows.

• Partner with GTM (Sales, Marketing, RevOps) and Finance stakeholders to identify automation opportunities and translate them into agent-based solutions.

• Develop and maintain MCP servers and/or an MCP gateway to connect agents securely to internal and third‑party systems (CRM, ERP, data warehouses, ticketing, etc.).

• Stand up and manage local LLM environments and Retrieval‑Augmented Generation (RAG) pipelines for use cases requiring data privacy, low latency, or offline operation.

• Build and maintain an agent harness (orchestration, tool‑calling, memory, guardrails, logging, evaluation) around local and hosted models.

• Write production‑quality Python (and other languages as needed) to support agent tooling, data pipelines, and integrations.

• Establish testing, monitoring, and evaluation practices for agent reliability, cost, latency, and output quality.

• Document architecture, runbooks, and guardrails for all deployed automations and agents.

• Stay current on the AI/agent tooling landscape and recommend improvements to the team's automation stack.
  

About you

Must-haves:

• Automation & agent development with Claude:
  – Hands‑on experience building automations/agents with the Claude Desktop application and the Claude API.

• Domain experience:
  – Prior work building agents or automations for GTM (Sales, Marketing, RevOps, Customer Success) and/or Finance use cases.

• Programming:
  – Proficient in Python, plus familiarity with other languages relevant to AI/automation work (e.g., TypeScript/JavaScript, Bash).

• MCP (Model Context Protocol):
  – Experience building and managing MCP servers directly, or operating agents through an MCP gateway.

• Local LLM & RAG:
  – Practical experience deploying and working with local/self‑hosted LLMs and building RAG pipelines (chunking, embeddings, vector stores, retrieval evaluation).

• Agent harness design:
  – Proficient in building an agent harness around local LLMs — orchestration, tool use, memory, guardrails, and evaluation loops.

Nice-to-haves:

• Experience with vector databases (e.g., Pinecone, Weaviate, Chroma, pgvector).

• Familiarity with GTM systems such as Salesforce, HubSpot, or similar CRM/marketing platforms.

• Familiarity with Finance systems (ERP, billing, or FP&A tooling).

• Experience with CI/CD, containerization (Docker), and cloud platforms (AWS/Azure/GCP).

• Understanding of AI safety, data privacy, and security best practices for enterprise agent deployments.
  

About us

At Keepit, we're on a mission to make cloud data protection simple, reliable, and built to last. Our platform provides customers with an immutable, historical archive of their data in systems such as Microsoft 365, Google Workspace, Salesforce, Entra ID, Dynamics 365, and Zendesk.

We protect our customers against everything, from ransomware to simple accidents.

We pride ourselves on backing up hundreds of petabytes of data in a performant, reliable, and predictable way.

As we collaborate across locations, English is our primary language.

We offer:

• Official employment (Umowa o pracę).

• 4 additional working days of vacation per full calendar year.

• 3 days of internal sick leave without a doctor's note.

• Health and life insurance.

• Employee Capital Plan (PPK).

• Multisport card compensation.

• Coverage of professional training, meetups, and conferences.

• English‑speaking club with native speakers and Polish language classes.

• Internet and glasses reimbursement.

• Office in Krakow city centre (Dluga 72) with beverages, fruit, and snacks.

• Regular team‑building events, winter and summer parties.

We kindly ask you not to provide us with any sensitive categories of personal data when applying for a job with us. When applying for the vacancy, Keepit will process your personal data, and therefore we recommend that you also read our privacy policy, which describes our processing of personal data and your rights as a data subject.

If you notice any misconduct or irregularities that fall within the scope of our whistleblowing procedure, please click here to report them.