Senior AI Engineer, Agentic Platform
New
W
WorkWaveOperational SaaS
Remote (UK-based) with occasional collaborative team meetups.Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years building production software or data-intensive systems used by real customers
- Required Skills
- AWSPythonSQL
Requirements
- Have 5+ years of experience building production software or data-intensive systems used by real customers.
- Bring strong Python skills and have shipped at least one LLM or agent feature to production users.
- Have hands-on AWS experience; Amazon Bedrock and Bedrock AgentCore experience is preferred.
- Have experience with agent orchestration, tool and function design, context assembly, and multi-step workflows.
- Have built retrieval over real business data and be able to explain context selection and answer failures.
- Bring SQL and metric fluency sufficient to identify when an agent uses the wrong number.
- Have built or owned an evaluation loop for a generative system, including labeled sets and regression gates.
- Have shipped product decisions about when an agent should answer, ask, refuse, and show its work.
- Have quantified agent outcomes such as adoption, task success, or decision quality and presented them to non-technical stakeholders.
- Have used coding agents on production work and be able to critically verify their output.
- Have excellent communication and collaboration skills across technical and non-technical teams.
Responsibilities
- Build production agents and the tools they call, including retrieval, multi-step workflows, and action-taking, on Amazon Bedrock.
- Turn semantic-layer capabilities and service APIs into endpoints and tools agents can use effectively.
- Shape the customer experience, including answer speed, confidence, explanations, and next steps.
- Build an evaluation harness with labeled test sets, groundedness and hallucination measures, and CI regression gates.
- Measure adoption, feedback, intent, and realized customer impact, and report results to Product and the business.
- Instrument tracing, diagnose answer failures, and turn failure modes into fixes.
- Own and operate the serving path, including MCP endpoints, latency, cost per response, caching, and runtime guardrails.
- Partner with Product Managers and engineers on agent-supported decisions and drive data or infrastructure changes with the platform team.
View Full Description & ApplyYou'll be redirected to the employer's site
