Forward Deployed Engineer (Applied AI / LLM Agents)

Jobgether; Ireland; Remote; EUR 35,000 - 70,000; Full time

Benefits offered by this job

Fully remote

High-impact responsibilities

Ownership and autonomy

Collaborative environment

Direct leadership exposure

Job summary

Jobgether is seeking a Forward Deployed Engineer (Applied AI / LLM Agents) based in Ireland. You will bring cutting-edge AI solutions into real business environments, working with customers to understand workflows, design tailored AI agents, and move prototypes toward production.

You’ll own technical delivery from discovery through deployment, integrate AI with existing tools via REST APIs, and collaborate with a small team shaping the roadmap.

Qualifications

• 5+ years of software engineering or applied AI experience, customer-facing.
• Proven ability to deploy production-grade LLM systems (RAG, AI agents).
• Strong Python/TypeScript and SQL/database knowledge.
• Experience integrating systems via REST APIs and webhooks.
• Ability to work independently and communicate clearly.
• English at C1 level or above.

Responsibilities

• Lead technical discovery sessions to map workflows into technical requirements.
• Design, develop, and deploy LLM-based agents and workflows to production.
• Integrate AI solutions with clients' tools via REST APIs and webhooks.
• Create reusable integration components standardised across environments.
• Define evaluation metrics and monitor deployed solutions.
• Communicate progress and findings to technical and business stakeholders.
• Travel occasionally to the United States when required.

Skills

Python

TypeScript

SQL

REST APIs

Webhooks

Communication

English (C1)

Ownership mindset

Tools

LangGraph

Model Context Protocol (MCP)

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Forward Deployed Engineer (Applied AI / LLM Agents) based in Ireland.

As a Forward Deployed Engineer, you will bring cutting-edge AI solutions into real business environments, turning complex operational challenges into practical, production-ready applications. You will work closely with customers to understand their workflows, identify opportunities for automation, and design tailored AI agents and intelligent workflows. Combining strong software engineering expertise with applied AI knowledge, you will take solutions from initial discovery and prototyping through deployment and ongoing optimisation. You will primarily support small and mid-sized businesses, integrating AI capabilities into their existing technology ecosystems. Working within a small, experienced team, you will have significant ownership over technical delivery while contributing directly to product development and innovation.

Accountabilities

• Lead technical discovery sessions with customers, mapping their workflows, data, systems, and stakeholders to translate business needs into clear technical requirements.
• Design, develop, and deploy LLM-based agents and workflows, taking solutions from early prototypes to production-ready implementations.
• Integrate AI solutions with existing customer tools, databases, and business software through REST APIs, webhooks, and third-party platforms.
• Develop reusable integration approaches and technical components that can be standardised across different customer environments.
• Establish evaluation frameworks and success metrics to measure solution performance, reliability, and business impact.
• Monitor and optimise deployed solutions, focusing on quality, operational costs, and latency.
• Communicate project progress, technical findings, results, and recommendations to both technical and business stakeholders.
• Share customer insights and implementation feedback with the product team to help shape the technical roadmap.
• Travel occasionally to the United States when required.

Requirements

• 5+ years of experience as a software engineer, full-stack engineer, or applied AI engineer, ideally in a customer-facing, founding, or product-oriented role.
• Demonstrated experience building and deploying production-grade LLM systems, including Retrieval-Augmented Generation (RAG), AI agents, prompt engineering, and evaluation frameworks.
• Strong programming skills in Python and/or TypeScript, alongside solid SQL and database knowledge.
• Hands-on experience integrating systems through REST APIs, webhooks, and third-party platforms.
• Strong ownership mindset, with the ability to work independently, manage ambiguity, prioritise effectively, and drive projects through to completion.
• Excellent communication skills, with the ability to explain complex technical concepts clearly to different audiences.
• English proficiency at C1 level or above.

Additional experience that would be an advantage:

• Previous experience as a co-founder, founding engineer, or technical lead, with responsibility for both product and technology decisions.
• A background in machine learning or data engineering combined with practical product development experience.
• Hands-on familiarity with AI agent frameworks such as LangGraph, Model Context Protocol (MCP), or similar technologies.
• Experience working with cloud platforms such as AWS, Azure, or Google Cloud Platform (GCP).
• Experience in product-led technology companies, ranging from established technology organisations to startups.
• Previous experience implementing enterprise platforms such as ERP or CRM systems within customer environments.

Benefits

• Competitive annual gross salary: €35,000-€55,000 for candidates with 5-6 years of experience, and €50,000-€70,000 for candidates with more than 6 years of experience.
• Fully remote working: Work remotely with the flexibility and autonomy to organise your own schedule.
• High-impact responsibilities: Contribute directly to the development and deployment of production-grade AI products.
• Ownership and autonomy: Take responsibility for technical projects and influence how AI solutions are implemented across customer environments.
• Collaborative environment: Join a small, experienced team working at the forefront of applied AI and LLM technologies.
• Direct leadership exposure: Work closely with the leadership team and contribute to important technical and product decisions.