Agentic AI Engineer

Vallum Associates

LLM EngineermidLondon Area, United KingdomonsitecontractBanking and Financial ServicesGitHub CopilotDatabricks Genieagentic AI workflowsCI/CD pipelinesautomated testingquality engineeringDevOpsposted 14 Sep
Unlock apply linkApply links and the original listing are a Pro feature: £4.99/mo or £25 once.

Description

We're looking for an Agentic AI Engineer to join our. In this role, you will design and implement agentic AI workflows that automate and accelerate software development activities , including coding, testing, quality assurance, and continuous integration. You will translate business requirements into practical AI-driven engineering solutions integrated with repositories, architecture, and CI/CD pipelines. The position involves building safe, controllable, and reusable AI patterns , ensuring proper validation, quality gates, and human oversight.a

Responsibilities

  • Translate business requirements into

agentic AI workflows

across coding, review, testing, and defect resolution

  • Build

connected AI-driven pipelines

that can develop code, execute tests, analyze failures, and refine implementations iteratively

  • Assess existing

repository, architecture, and technology stack

before proposing automation solutions

  • Embed

validation controls, quality gates, evidence capture, safe stopping conditions, and human approval checkpoints in solutions

  • Package and integrate

agentic AI workflows for reuse

across teams and development environments

  • Ensure measurable outcomes aligned with

quality, security, and regulatory compliance

  • Collaborate with engineering, QA, and DevOps teams to scale

AI-driven capabilities

across the organization

  • Support continuous improvement and responsible AI practices

Requirements (Must Have Skills)

  • Strong hands-on background in

software engineering, SDET, quality engineering, data engineering, DevOps, or platform engineering

  • Proven experience using

agentic AI tools

such as GitHub Copilot and/or Databricks Genie

  • Expertise in

multi-step AI workflows

for development lifecycle: code generation, review, testing, and iterative refinement

  • Proficiency in

automated testing, shift-left quality practices, Git-based workflows, pull requests, and CI/CD

  • Ability to

translate business problems into technical AI solutions

with measurable control points

  • Experience embedding

human-in-the-loop validation, safe failure handling, and reusable automation patterns

Nice to Have Skills

  • Experience creating

custom Copilot agents or repository-aware AI prompts

  • Familiarity with

Databricks workflows, notebooks, pipelines, and data-quality engineering

  • Knowledge of

AI agent evaluation, regression testing, and performance benchmarking

  • Exposure to

static analysis, security testing, observability solutions, and responsible AI governance

  • Experience scaling

AI engineering capabilities across large programs or multiple teams