AI Engineer - London at Sequence

London, United Kingdom

true · full_time · {"@type":"MonetaryAmount","currency":"GBP","value":{"@type":"QuantitativeValue","minValue":115000,"maxValue":130000,"unitText":"YEAR"}} · Visa sponsorship

Apply for this role at Sequence

Responsibilities:
- Design, build and own AI infrastructure for production LLM systems: agentic workflows, prompt iteration, tool integration and evals.
- Implement AI‑powered approval workflows that translate natural‑language rules into deterministic, auditable business logic.
- Develop intelligent agents (e.g., collections agent) that run configurable, autonomous workflows with proper context handling and observability.
- Ensure model safety and reliability: threat analysis, sandboxing, testing, monitoring and degradation strategies.
- Collaborate with product and backend teams to ship end‑to‑end features and maintain production quality and latency SLAs.

Requirements:
- Proven track record shipping LLM‑based systems to production and familiarity with failure modes in real customers' environments.
- Experience designing agentic systems, eval frameworks and prompt engineering practices.
- Strong backend engineering skills and production experience (Kotlin/Java, Postgres, GCP/Vertex AI, Terraform, TypeScript a plus).
- Practical knowledge of AI security, testing (e.g., prompt regression tests), monitoring, and tooling (Langsmith, evals, embeddings, memory).
- Comfortable with ambiguity, product‑led development, and building reliable, auditable systems for business‑critical workflows.