W
Senior AI Engineer, Agentic Platform
Contract type
Ongoing
Work mode
Remote
Experience
Senior · 5+ years
Job description
A product-minded AI engineer role at WorkWave to build and own production AI agents for AskWaive, the in-product assistant, focusing on quality, coverage, evaluation, and customer impact.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Remote
What you'll do
- Own the outcome: start from the customer and stay with it until the agent answers their needs better
- Build production agents and the tools they call—retrieval, multi-step workflows, action-taking—on Amazon Bedrock, with Bedrock AgentCore as the runtime and tools exposed over MCP
- Turn the semantic layer and service APIs into endpoints and tools an agent can wield well, knowing which metrics and entities it should reach
- Shape the experience: speed, confidence, explanation, and next step offered by an answer
- Build the eval harness—labeled test sets, groundedness and hallucination rates, and CI gates that stop regressions before they ship
- Measure adoption, feedback, and intent, then report realized impact back to Product and the business in numbers
- Instrument tracing that shows why an answer was wrong, turn each failure mode into a specific fix, and ship again
- Own the serving path—MCP endpoints, latency, cost per response, caching, and runtime guardrails
- Partner with Product Managers and engineers on which decisions an agent should support and which it shouldn't
- Drive change alongside the platform team where data or infrastructure limits what an agent can do
- Build with coding agents: set direction and targets, review output critically, and build harnesses—scaffolding, context, tests, review loops
What we're looking for
- 5+ years building production software or data-intensive systems used by real customers, with strong Python skills
- At least one LLM or agent feature shipped to production users
- Hands-on AWS experience, ideally Amazon Bedrock and Bedrock AgentCore
- Agent engineering experience: orchestration, tool and function design, context assembly, and multi-step workflows
- Retrieval and domain grounding experience over real business data, with enough SQL and metric fluency to catch an agent answering with the wrong number
- Experience building or owning an eval loop for a generative system—labelled sets, regression gates, and a defensible number
- Product sense for AI: opinions about when an agent should answer, ask, refuse, and show its work, and shipped those opinions
- Experience quantifying what an agent delivered for users—adoption, task success, decision quality—and presenting it
- Experience using coding agents on real production work and investing in harnesses
- Excellent communication and collaboration skills, with a track record of working across technical and non-technical teams
- Applicants must currently have the legal right to work in the UK
Nice to have
- LLM observability tooling (Langfuse, LangSmith, or Arize)
- Semantic layer or metrics-layer design (Ossie, dbt)
- Field-service, logistics, or other operational SaaS domains
- Prior experience as a senior or lead engineer responsible for guiding technical direction
Benefits
- Competitive company pension scheme with employer match
- Generous holiday allowance / flexible time off plus UK bank holidays
- Enhanced maternity, paternity, and parental leave policies
- Ongoing learning resources
- Comprehensive Employee Assistance Programme (EAP) providing free 24/7 mental health, legal, and financial guidance
Apply
About WorkWave
Laid back but focused: We offer a flexible, collaborative work environment and a passion for developing innovative, best-in-class solutions that directly contribute to the success of our customers. Impact-driven: We care deeply and deliver services and solutions that make a real difference in the lives of our clients and their businesses. Trust & Inclusion: We openly accept others as they are and build strong partnerships based on trust and mutual respect.
What they value
- Laid back but focused
- Impact-driven
- Trust & Inclusion