Summary
* About: Kalisa is a GenAI platform turning knowledge and expertise into secure AI solutions, in minutes.
* Core skills required: Python, Flask, LangChain, RAG, Generative AI product development, LLMs, Guard railing, anti-hallucination techniques and GenAI evaluation techniques.
* Other skills considered: Tailwind CSS, HTMX, AWS or Azure or GCP
* Please only apply if you are fully eligible to work in the UK
Who we are
Kalisa is a fast-growing AI start-up enabling the next generation of professional services. Our platform helps organisations turn their knowledge and expertise into chat agents, automated workflows and AI-powered experiences - securely, reliably, and at scale.
We are based in the UK and service a rapidly growing client base around the world. Due to this continued growth we are expanding our engineering team to help us scale our platform and build new functionality.
We are at the start of the GenAI revolution, and this is an opportunity like no other. If you think you are the right person for the role, we encourage you to apply and look forward to hearing about your tech journey.
Who you are
* We are seeking an experienced Flask Python AI Engineer with LangChain Experience with a proven track record in building and deploying production-grade GenAI applications.
* You will join a small, agile, and passionate team to enhance and scale our GenAI platform.
* This will involve working closely with our team to deliver new features, improve existing functionality, and ensure seamless integration with new foundation models as they become available.
* You will be able to work independently, be self-sufficient, eager to learn, be able to build something from scratch and see it through to completion.
As a key team member, you will:
* Architect & Implement: Design, build, and maintain reliable, scalable, and high-performance Python services within a Flask-based ecosystem.
* Front-End Enhancement: Leverage HTMX and Tailwind CSS to create an engaging, dynamic and responsive user interface, minimising JavaScript overhead and improving the overall user experience. No prior HTMX experience is required.
* GenAI Integration: Work with LangChain to implement prompt engineering techniques, RAG pipelines, and intelligent agent capabilities.
* RAG & Vector Databases: Implement and optimise RAG strategies, semantic search capabilities, and embeddings-based retrieval; integrate and manage vector databases.
* Relational Databases: Leverage MySQL and SQLAlchemy as the ORM to design robust, optimised schemas and implement efficient data retrieval and storage strategies.
* Cloud Deployment: Integrate and deploy services across cloud platforms (Azure, AWS, GCP), ensuring robust infrastructure, monitoring, and observability.
* Data Security & Compliance: Collaborate with security teams and architects to ensure data privacy, compliance, and reliable access controls within enterprise environments.
* Continuous Improvement: Participate in code reviews, contribute to technical documentation, and proactively identify opportunities for platform optimisation and enhancement.
Requirements
Professional Experience:
* Python Proficiency: Minimum of 5 years of experience working with Python, the Flask framework, developing relational database-driven backend services, APIs and web apps.
* Front-End Integration: Demonstrable experience of working with Tailwind CSS to implement responsive website and web app designs.
* GenAI Expertise: A minimum of 2 years of experience building and shipping at least one GenAI product (e.g., LLM-based app, custom chatbot, RAG-driven knowledge platform).
* LangChain: Demonstrable experience working with LangChain.
* RAG & Vector Technologies: Demonstrable knowledge of RAG techniques, vector databases, semantic search, and embedding models.
* Responsible AI: Guard railing, anti-hallucination techniques and GenAI evaluation techniques.
Nice to have:
* Front-End Integration: Working knowledge of HTMX to build dynamic web applications.
* Cloud Platforms: Practical experience deploying and managing applications on at least one major cloud provider (Azure, AWS, or GCP).
Additional Requirements:
* Based in the UK and authorised to work.
* Strong communication skills and the ability to work effectively in a fully remote team environment.
* Fluent English speaker and writer.
* Most of our work is in written form, which means being a good writer is very important. The importance of high-quality writing is carried through our designs, internal project discussions, code comments and the code itself.
* Self-starter mentality with a focus on delivering tangible results.
What We Offer
* Competitive Pay: Based on your experience to date.
* Fully Remote: Enjoy the freedom to work from anywhere in the UK.
* Pension
* 25 Days Holiday + Bank Holidays
* High Impact Work: Contribute to a fast-growing platform already used globally, enhancing your experience and portfolio.
* Career Growth Opportunities: Work at the intersection of cutting-edge AI research, product innovation, and world-class engineering practices.
* Latest Cloud & AI Technology: From AWS, Azure and GCP.
* Learning and Development Opportunities: Including access to resources and mentorship.
* A Friendly, Supportive and Passionate Team.
Our Hiring Process
* 10 min video demonstration: We will ask you to record a 10 mins video showcasing a LangChain (ideally!) GenAI project you have built or took part in developing, clearly showcasing and explaining the application of LLMs and vector embedding of external documents or data, guard railing, anti-hallucination techniques and GenAI evaluation techniques.
* Initial Interview, including GenAI project walkthrough: Meet with our CEO for an in-depth discussion about your experience, approach, and technical skills. This is an opportunity for us to get to know each other and ensure we share the same vision and values. We will discuss the GenAI project you showcased in the previous step, and discuss your design decisions, implementation details, and the overall outcome, giving us a chance to understand your problem-solving approach and coding style.
* Technical Challenge: If you are successful in the initial interview, you will be invited to complete a technical challenge that will be briefed based on your experience. We expect this to take 1-2 days, and you will be compensated for your time.
If you are excited about pushing the boundaries of what is possible with GenAI and you meet the above criteria, we would love to hear from you.
** Direct applications only - No recruiters **