Founding Software Engineer

Founding Software Engineer

Expected outcomes:

• Design and implement production-grade AI systems with focus on LLMs and autonomous agents
• Develop optimized RAG systems and embedding pipelines
• Build robust Python applications emphasizing async programming and performance
• Deploy, monitor and maintain AI systems in production
• Establish a scalable and maintainable technical foundation, balancing speed of delivery with long-term scalability
• Champion the use of AI, staying at the forefront of Agentic AI advancements, and apply these learnings to deliver value-driven solutions.
• Be part of building our performance-driven culture that values transparency, simplicity, and rapid iteration - you will be part of the basis of our culture
• Foster a culture of learning and innovation, enabling the team to adapt to the rapidly evolving AI landscape.

All the desired skills we are looking for

• You have experience building in a fast-iteration environment - ideally with start-up experience
• You solve problems quickly and enjoy delivering outcomes, not just fancy technology
• You love learning and being part of a high-performing team
• Data-first - you love thinking on a data-first mindset and its possibility to create better products, experiences and business models down the line
• You’ve been deploying agent architectures / LLMs in production and at scale

On a technical note, our stack below - we look for people that can combine a part (or all if possible) of the technical skills defined below

Python expertise

• Async programming, API development, real-time ASGI, Django/Channels
• Testing, logging, monitoring, performance optimization
• Production-grade application development
• Knowledge of data storage solutions (both SQL and NoSQL)
• Async message queues (Celery + RabbitMQ / Redis)
• Experience with high-throughput, low-latency systems

LLMs usage

• Strong understanding of LLMs, prompt engineering, chaining, caching and model fine-tuning
• Experience with both open-source and closed-source LLMs
• Experience with Retrieval-Augmented Generation (RAG), embedding optimization, chunking strategies, vector databases (ChromaDB, Pinecone)
• Experience with LLM frameworks (Llamaindex / Langchain)
• Model evaluation metrics and performance benchmarks
• LLM guardrails and security best practices
• LLM cost-optimisation strategies