Swoep is hiring an AI Engineer 

Join a team building production-grade LLM agents and AI features used in real products. You’ll design, implement, and evaluate agents, ship reliable APIs, and collaborate closely with full stack engineers. 

What you’ll do 

• Build on our internal AI framework and create lightweight wrappers and SDKs 
• Design, implement, and evaluate LLM-based agents in production 
• Work with OpenAI or other LLM APIs and related tooling 
• Handle deployments and infrastructure with an eye for reliability 
• Collaborate with full stack engineers to ship end-to-end features 
• Stay current with AI research and apply ideas pragmatically 

Must haves 

• 2 to 3+ years in AI or software engineering 
• Strong Python skills with OOP and clean modular code 
• Experience with LLM APIs and prompt or context engineering fundamentals 
• Cloud experience is required. Azure preferred, AWS or GCP also fine 
• Comfortable with deployment workflows and basic infra 

Nice to have 

• Experience with context engineering at scale, prompt orchestration, or fine-tuning 
• Vector databases, embeddings, or RAG pipelines 
• Terraform or other IaC tools 

How we work 

• Stable core is in place. Your focus is refinement, reliability, and scaling 
• Hybrid setup with 3 days in office 
• Fast iterations, clear ownership, low overhead 

About Swoep.ai 

We’re an AI startup focused on letting teams query their data warehouse in natural language and automate workflows with agents. Customers in logistics and healthcare run Swoep to reduce manual ops and speed up decisions. You’ll help evolve a production platform where research meets delivery and impact is measured in shipped features. 

Interested?

Send me a message here on LinkedIn about how you see yourself contributing to Swoep.AI.