AI Engineer

Epiminds AB; Stockholms kommun; On-site; SEK 900,000 - 1,300,000; Full time

Benefits offered by this job

Competitive salary and equity

Healthcare and retirement savings

Office catering

Office catering

Job summary

A leading AI systems company in Sweden seeks an experienced model integration engineer to design and implement production-ready AI capabilities. You will work on developing autonomous multi-agent systems, integrating advanced LLMs and ensuring safety and performance metrics. The role requires strong software engineering skills and a collaborative mindset to translate technical capabilities into impactful user experiences. Competitive salary and equity are part of the offer.

Qualifications

• 3+ years working with production ML/AI systems, ideally with agentic or multi-agent architectures.
• Practical experience integrating LLMs and multimodal models into applications.
• Strong software engineering skills with production-grade system design and testing.
• Experience with retrieval systems, vector databases and feature stores.
• Proven track record shipping end-to-end data, models, and monitoring.
• Bias and safety oriented with measurable mitigation strategies.

Responsibilities

• Implement and iterate agent policies, task planners and orchestration.
• Integrate LLMs and multimodal models with serving infrastructure.
• Design evaluation systems for agent performance and correctness.
• Collaborate with product, design and customer success to drive impact.

Skills

Production ML/AI systems

Integration of LLMs and multimodal models

Strong software engineering skills (Python, TypeScript)

Retrieval systems and vector databases

Evaluation mindset and design metrics

Collaborative approach

Tools

Python

TypeScript

LLMs integration

Vector databases

Feature stores

Retrieval systems

Job description

Epiminds is building the next generation of marketing systems.

We’re live with 22 leading agencies managing 420 brands on a closed waitlist, with 1,300+ more waiting for access. Backed by a $6.6M Lightspeed-led round.

Role Mission 🎯

Turn cutting-edge AI research and agentic systems into reliable, production-ready capabilities that empower Lucy and her team. You will design, implement and scale models, orchestration, and evaluation pipelines so our autonomous agents perform safely, efficiently and transparently in real customer workflows.

Core Responsibilities

• Agent Development & Orchestration - Implement and iterate agent policies, task planners and chain-of-action orchestration. Improve how agents coordinate, delegate and surface their reasoning to users.

• Model Integration & Infrastructure - Integrate LLMs and multimodal models (inference and streaming) with robust, cost-effective serving infrastructure. Build observability into model usage, latency, and cost.

• Evaluation & Safety - Design automated and human-in-the-loop evaluation systems for agent performance, correctness and alignment. Implement safeguards, mitigation strategies and monitoring for risky behaviours.

• Data & Feature Engineering - Own pipelines for training, fine-tuning, retrieval-augmented generation (RAG) and vector search. Curate datasets and features that improve agent reasoning and factuality.

• Cross-functional Collaboration - Work closely with product, design and customer success to translate capabilities into memorable user experiences and measurable business impact.

What We're Looking For

• 3+ years working with production ML/AI systems, ideally with agentic or multi-agent architectures.

• Practical experience integrating LLMs and multimodal models (API-based or self-hosted) into applications.

• Strong software engineering skills (Python, TypeScript or similar) with production-grade system design and testing.

• Experience with retrieval systems, vector databases and feature stores preferred.

• Track record of shipping end-to-end systems: data, models, infrastructure and monitoring.

• Bias, safety and evaluation mindset — able to design metrics and mitigation strategies for real-world deployments.

• Collaborative, high-ownership approach and clear communication with cross-functional partners.

Why Epiminds

Epiminds is a small, high-ownership team built by people from Google and Spotify, backed by investors behind Anthropic, xAI, and Mistral.

We’re building autonomous, multi-agent AI systems that represent the next evolution of marketing, not as a future vision, but in production today, used by agencies and brands at scale.

What We Offer

• Competitive salary and meaningful equity.

• Healthcare, retirement savings, wellbeing support.

• Office catering.

Recruitment Process

1. Recruiter screening.

2. Technical task.

3. Code Interview.

4. Trial with us in the office.

Epiminds is an equal opportunity employer. We welcome applicants of all backgrounds and are committed to creating an inclusive environment for everyone.