Epiminds
AI Engineer
OnsiteStockholm, SwedenApplications closedMarTech
Our Take
Build production-ready autonomous, multi-agent AI systems using LLMs and orchestration pipelines.
What you’ll do
- Implement agent policies, task planners, and chain-of-action orchestration
- Integrate LLMs and multimodal models into serving infrastructure
- Design automated evaluation systems for agent performance and safety
- Own pipelines for training, fine-tuning, RAG, and vector search
What they’re looking for
- 3+ years with production ML/AI or multi-agent architectures
- Experience integrating LLMs and multimodal models into applications
- Strong software engineering skills (Python, TypeScript)
- Familiarity with retrieval systems, vector databases, and feature stores
What you get
- Competitive salary and meaningful equity
- Healthcare, retirement savings, wellbeing support
- Office catering
Skills & Focus Areas
- AI/ML
- LLMs
- Agentic Systems
- Multimodal Models
- RAG
- Vector Databases
- Python
- TypeScript
- System Design
As posted by Epiminds
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
Recruiter screening.
Technical task.
Code Interview.
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.