Senior LLM Backend Engineer (Remote, Spain)

About Bark

Bark is revolutionising the way people find professionals in over 1,000 unique categories. As the UK's largest and fastest-growing services marketplace, we're on a mission to make finding the right professional quick and easy. With a presence in eleven countries and plans for further expansion, joining us at this genuinely exciting time will be a journey like no other.

Our cutting-edge technology ensures that you can always find the best professional for any job. With a talented team of over 250 dedicated individuals, we're committed to providing exceptional service and ensuring that our customers are satisfied every step of the way. This is an exciting time to join our scaling business, we recently placed in the Sunday Times Best Places to Work 2024.

As a profitable scale-up, Bark is in a unique position to offer the best of both worlds; the excitement and agility of a start up combined with the financial security and backing of a renowned private equity firm, EMK Capital. You'll have ownership, agility, responsibility and stimulation without any of the worry.

*Please note you must be based in Spain to be considered for this fully remote role

About the Role

We are looking for a Senior Backend Engineer with a strong focus on Large Language Models (LLMs) to join one of our product squads. You’ll be responsible for designing, implementing, and optimising LLM-powered features, working closely with product managers, designers, and engineers to bring AI capabilities directly into our products.

You’ll own the full lifecycle of LLM integration, from experimentation and prototyping, to production deployment, to ongoing optimisation. You’ll also help shape our AI architecture, ensuring that LLM features are scalable, efficient, and cost-effective.

Our backend is written in Python, and you’ll use it alongside AI integration tools, APIs, and frameworks to create innovative features in areas such as personalisation, conversational interfaces, AI-assisted analytics, and automated decision-making.

Responsibilities

• Work with product managers to understand user needs and translate them into AI-powered functionality.

• Design and build APIs, services, and workflows that integrate LLMs (both proprietary and open-source).

• Implement prompt engineering, RAG pipelines, and model fine-tuning where required.

• Optimise AI inference performance, scalability, and cost-effectiveness.

• Ensure AI features meet high standards for security, reliability, and maintainability.

• Collaborate with other engineers to integrate AI features seamlessly into the wider system.

• Stay on top of emerging LLM technologies and best practices, running experiments and sharing knowledge across the team

Required Skills and Experience

• Extensive production experience with Python in backend engineering.

• Proven experience integrating LLMs into applications via APIs or SDKs.

• Strong experience building and maintaining:

• APIs for LLM-based features

• Event-driven workflows

• Business logic that consumes AI outputs

• Integrations with 3rd party AI/ML platforms

• Solid SQL and NoSQL experience (especially in AI data pipelines).

• Production experience with Docker, ideally with Kubernetes or AWS Fargate/ECS/EKS.

• Experience deploying and maintaining AI services in cloud environments.

• Strong organisational skills and ability to deliver in a fast-paced, product-focused

Desired skills and experience

• Familiarity with LangChain, LlamaIndex, or similar LLM orchestration frameworks.

• Experience with vector databases (e.g. Pinecone, Weaviate, FAISS, Elasticsearch).

• Knowledge of prompt engineering and evaluation techniques.

• Knowledge of and experience with agentic workflows and MCP.

• Familiarity with cloud monitoring tools (e.g. Datadog) for AI systems.

• Interest in usin