Senior Software Engineer (Artificial Intelligence)

Muck Rack; Ireland; Remote; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Fully distributed - remote environment

Geo-neutral compensation

Time off - 4+ weeks + holidays

Health, vision, dental insurance

401k retirement contribution 3%

Paid parental leave

Full WFH setup reimbursement

Learning & development access

No meeting Fridays

Job summary

Muck Rack is building AI agents for PR and communications pros. You’ll take features from idea to production across our Python agent runtime, MCP server, and Django/Vue app. You’ll help decide how the technology works, ship it to real customers, and learn from how they use it.

You’ll shape what we build next, work with new models, and solve real customer problems. If you want to build agents people rely on, we’d like to meet you.

Qualifications

• Experience measuring AI quality and using data to improve it.
• Strong API and tool design skills, including authentication and authorization.
• Fluent Python skills with async programming and frameworks like FastAPI, FastMCP, or Django.
• 7+ years building production software.
• Proactively incorporates AI tools to improve productivity and delivery.
• Understanding prompting, tool use, context management, and failure modes in models.
• Experience shipping LL-powered features or agents to real customers exposing tools via MCP.
• Overlap with US time zones (Eastern preferred).
• Experience with LLM observability and AI evaluation methods (e.g., DeepEval).
• Knowledge of streaming UIs, server-sent events, and Vue.js.
• AI security, including prompt injection defenses and tenant isolation.
• Agent frameworks such as Pydantic AI, LangGraph, or OpenAI Agents SDK.

Responsibilities

• Build features from idea to production across our Python agent runtime, MCP server, and Django/Vue app.
• Shape how technology works, ship to real customers, and learn from usage.
• Design agents that plan and execute multi-step workflows with memory and guards.
• Develop tools, prompts, and multi-turn workflows with decision points and handoffs.

Skills

Python

API design

LLM tooling

Django

Vue.js

MCP server

Remote collaboration

LLM observability

Streaming UIs

Prompting fundamentals

AI security

Agent frameworks

Tools

FastAPI

FastMCP

Django

Vue.js

MCP server

Pydantic AI

LangGraph

OpenAI Agents SDK

Job description

• Our Agents team at Muck Rack is building AI for PR and communications professionals. Our first agent helps customers understand their media coverage. Next, we’re building agents that can plan and carry out multi-step workflows
• You’ll take features from idea to production, working across our Python agent runtime, MCP server, and Django/Vue application. You’ll help decide how the technology works, ship it to real customers, and learn from how they use it
• You’ll help shape what we build next and how we build it. You’ll work with new models, solve real customer problems, and take your ideas from experiment to production. If you want to build agents people actually rely on, we’d like to meet you
• Build agents that take action. Build tools, prompts, guardrails, and multi-turn workflows with memory. Help agents know when to act, ask a question, or hand off to a human
• Ship the full experience. Build in-product chat, streaming responses, permission-aware APIs, and our external MCP server
• Make quality measurable. Build evals, catch regressions, and use production feedback to improve quality, latency, and cost
• Help shape the platform. Make decisions about how we build, deploy, and run agents as the product grows

Benefits

• Fully distributed - Much Rack are committed to a permanent, fully remote environment, core to the way they do business.
• Geo-neutral compensation - Much Rack believe in equitable pay regardless of where you live.
• Time off - 4+ weeks off-the-grid vacation, sick and mental health days, and company holidays.
• Insurance - Health, vision, and dental coverage paid at 100% for individuals
• Retirement planning - MUck Rack contribute 3% of your annual salary to your 401k automatically.
• Paid parental leave - 8 weeks fully paid bonding for all parents + up to 8 weeks fully paid recovery from childbirth.
• Full WFH set up - Including monthly phone/internet reimbursement and coworking stipend.
• Learning & development - Take advantage of unlimited access to learning platforms and regular training opportunities.
• No meeting Fridays - Take control of your calendar, and make time for reflection and deep-focus tasks

Experience

• Experience measuring AI quality and using what you learn to improve it
• Strong API and tool design skills, including authentication and authorization
• Fluent Python skills, including async programming and experience with FastAPI, FastMCP, or Django
• 7+ years building production software
• Proactively incorporates AI tools into day-to-day work to improve productivity and accelerate delivery
• A practical understanding of prompting, tool use, context management, and where models go wrong
• Experience shipping LLM-powered features or agents to real customers including exposing tools via MCP
• Working-hour overlap with US time zones (Eastern preferred)
• Experience with LLM observability
• AI evaluation tools and methods, including DeepEval and LLM-as-judge
• Streaming UIs, server-sent events, and Vue.js
• AI security, including prompt injection defenses and tenant isolation
• Agent frameworks such as Pydantic AI, LangGraph, or the OpenAI Agents SDK
• MCP servers and LLM tooling