Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
NPWPosted 5 days ago

Senior AI Engineer

Who we'd reach at NPWFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Recruiter

In-house, owns the opening

Head of the team

Director or head of the group

Power Apply

From your own Gmail and LinkedIn.

How this role compares

One of 37 open Senior AI Engineer roles we are tracking today.

This posting does not state pay. The middle of the 15 that do advertises £98,000 – £115,000 a year.

Posted 5 days ago, with 9 of the others posted since and 27 still open from before.

Counted across the roles Frontrunner has open right now.

About the role

This remote senior role is for an engineer with at least two years of production experience who will build production AI components on a data-centric platform. The work covers agent logic, retrieval-augmented generation alongside knowledge graph reasoning, and evaluation and observability. The role asks for a practical focus on latency, quality and cost.

What you’ll do

  • Build and harden intent, planner and router agents with typed JSON inputs and outputs.
  • Implement document preparation, embeddings, hybrid retrieval and reranking for a RAG baseline.
  • Version and tune prompts, routing policies and model settings, and document cost and latency budgets.
  • Integrate evaluation sets and automated re-evaluation on any change.
  • Add tracing, metrics, logging and cost dashboards.
  • Enforce access controls, PII handling, moderation and human approval steps for state-changing actions.
  • Write tests, review pull requests and ship through CI/CD with feature flags.

What they’re looking for

  • Two to four or more years building production services.
  • Hands-on work with LLM tool calling, agent frameworks and prompt versioning.
  • Practical knowledge graph experience with RDF, SPARQL, property graphs or Gremlin.
  • Experience with RAG pipelines, chunking, embeddings and retrieval.
  • Familiarity with vector databases and search engines such as pgvector, Pinecone, OpenSearch or Elasticsearch.
  • Python and or TypeScript or Node.js proficiency, with API design skills.
  • OpenTelemetry, performance profiling and resiliency patterns.
  • Security practices such as OIDC, secrets management and audit logging.
  • Git-based workflows and automated testing.

Nice to have

  • Evaluation engineering including judge models, A/B testing and rubric design.
  • Async I/O, caching and token budget enforcement.
  • Containers, Kubernetes, service mesh and canary releases.
  • Explainability work with source lists and clear approval prompts.

What’s on offer

  • Remote working arrangement as listed.

Skills

Questions about this role

Is this role remote?

Yes, the role is listed as remote.

How many years of experience do I need?

The posting asks for at least two years of production experience, with two to four years mentioned for LLM engineering.

Do I need knowledge graph experience?

Practical knowledge graph experience is listed as required.