We’re supporting a Series B company building AI-native software to modernise how businesses operate and make decisions. Their platform combines large language models, workflow automation, and structured data systems to deliver intelligent product experiences that users rely on daily.
They're looking for an AI Engineer focused on applied AI systems, someone who can turn foundation models into reliable, production-grade product capabilities. This role is focused around real-world implementation: prompt engineering, retrieval systems, orchestration, evaluation, and backend integration rather than model research or training frontier models from scratch.
You’ll work closely with engineering, product, and design teams to ship AI features that are fast, trustworthy, and deeply integrated into the product experience.
What You’ll Do
Design and build LLM-powered product features using prompt engineering, structured outputs, tool usage, and function calling
Develop and improve retrieval-augmented generation (RAG) systems, including chunking strategies, embedding pipelines, indexing, and retrieval optimisation
Build orchestration layers for multi-step AI workflows involving agents, tools, memory, retries, and fallback handling
Integrate AI systems into backend services and production infrastructure
Evaluate model quality, latency, hallucination rates, and operational cost, then iterate to improve performance and reliability
Collaborate cross-functionally with product and design to create intuitive AI experiences with strong UX considerations
Experiment with emerging AI tooling, frameworks, and open-source models to improve product capabilities
Help define engineering best practices around observability, testing, evaluation, and safety for AI systems
What We’re Looking For
3+ years of experience building AI-driven products, ML-enabled applications, or backend systems with AI integrations
Strong hands-on experience working with modern LLM APIs and ecosystems (OpenAI, Anthropic, open-source models, etc.)
Solid Python engineering skills and experience building production backend services
Experience designing prompts, structured outputs, and tool-based workflows for real-world applications
Familiarity with retrieval systems, embeddings, vector databases, and semantic search concepts
Strong product instincts with attention to usability, responsiveness, and reliability
Comfortable operating in fast-moving startup environments with high ownership and ambiguity
Nice to Have
Experience building agentic systems with planning, tools, and memory
Familiarity with frameworks such as LangChain, LlamaIndex, DSPy, or similar orchestration tooling
Exposure to fine-tuning, adapters, evaluation pipelines, or synthetic data generation
Experience deploying AI workloads in cloud environments and monitoring production inference systems
Background working on workflow automation, productivity software, or AI copilots