Job Description

We are looking for a Mid-to-Senior AI Engineer to join our team.

This position is for someone with real, hands-on experience building AI systems that have gone beyond prototypes and have actually been deployed in production.

The focus areas include

• Large Language Models

• Natural Language Processing

• RAG and retrieval systems

• AI agents and agentic workflows

• Multi-agent architectures

• Tool calling and API-based AI actions

• AI evaluation, reliability, and monitoring

• Production-grade AI system design

We are especially interested in engineers who can take ownership of the full lifecycle: understanding the problem, designing the solution, building the system, testing it properly, deploying it, and improving it based on real usage.

You should have experience with things like

• Building LLM-powered products or internal systems

• Designing retrieval pipelines using embeddings, vector databases, metadata, and reranking

• Creating agents that can use tools, follow workflows, and interact with external systems

• Working with Python, APIs, databases, background jobs, and backend services

• Improving output accuracy, reducing hallucinations, and handling edge cases

• Knowing when to use AI and when to use simple deterministic logic instead

This is not a role for someone who has only built demo apps, followed tutorials, or experimented with AI tools casually.

Please apply only if you have already built and deployed LLM, NLP, agentic AI, or multi-agent systems in a real production environment.

When applying, please include your CV and a short description of one or two AI systems you have built, covering:

• What the system was built to do

• What your responsibilities were

• Which models, tools, frameworks, and architecture were used

• Whether it was deployed in production

• What technical challenges you had to solve

Applications without relevant production experience in AI systems will not be considered.