Senior AI Engineer – Agent Platform & Production Agents

TaskEasy; United Kingdom; Remote; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Pension with employer match

Generous holiday allowance

Enhanced parental leave

Learning resources

Employee Assistance Programme (EAP)

Job summary

TaskEasy seeks a product-minded AI engineer to turn customer needs into reliable agents and in-product assistants. You’ll own the end-to-end from customer need to endpoint, build production agents and tooling on AWS Bedrock, and shape experiences that drive measurable impact for users across the platform.

You will work with data platforms and the running runtime, establishing evaluation harnesses, groundedness metrics, and CI gates to prevent regressions while delivering fast, trustworthy

Qualifications

• 5+ years building production software or data-intensive systems used by real customers, with strong Python skills—including at least one LLM or agent feature you shipped to production users.

Responsibilities

• Own the customer need to turn it into a deployable agent and tools.
• Build production agents and the tools they call on Bedrock with MCP runtime.
• Turn semantic layer and service APIs into endpoints and tools an agent can wield.
• Shape the experience: focus on speed, confidence, explanations and next steps.
• Prove it: build eval harness, groundedness metrics, and CI gates.
• Measure adoption, feedback, and impact in numbers.
• Diagnose failures and iterate on fixes; ship again.
• Deliver: own serving path including endpoints, latency, caching, and guardrails.
• Embed and influence: partner with Product and engineers on agent decisions.

Skills

Python

LLM features

Agent engineering

AWS Bedrock

Data-intensive systems

Tools

Bedrock AgentCore

MCP

Job description

TaskEasy seeks a product-minded AI engineer to turn customer needs into reliable agents and in-product assistants. You’ll own the end-to-end from customer need to endpoint, build production agents and tooling on AWS Bedrock, and shape experiences that drive measurable impact for users across the platform.

You will work with data platforms and the running runtime, establishing evaluation harnesses, groundedness metrics, and CI gates to prevent regressions while delivering fast, trustworthy