AI-Driven Automated Testing Workflow Engineer
Budget: £10 – £20 GBP
We are seeking a highly skilled LLM Workflow Engineer to help design and implement AI-driven workflows for software testing automation. The ideal candidate will have hands-on experience building pipelines that integrate Large Language Models (LLMs), RAG (Retrieval-Augmented Generation), and test automation frameworks.
This role involves turning client requirements into automated test scenarios, generating and executing test code, and designing feedback/reporting loops that keep the workflow scalable, accurate, and reliable.
Responsibilities:
Design and build LLM-powered workflows that translate requirements into test scenarios and automation scripts.
Implement RAG pipelines for contextual test case generation and knowledge retrieval.
Integrate workflows with automation tools (e.g., Playwright, Selenium, or similar frameworks).
Set up pipelines for test execution, results analysis, and reporting.
Collaborate on refining prompt engineering, evaluation, and optimization for accuracy and reliability.
Ensure workflows can be extended and integrated into CI/CD environments.
Required Skills:
Strong background in Python (LangChain, LlamaIndex, or similar frameworks).
Experience with LLMs (OpenAI, Anthropic, or local models like Llama/Mistral).
Knowledge of RAG architectures (vector databases such as Pinecone, Weaviate, FAISS, or Milvus).
Experience with test automation frameworks (Playwright, Selenium, or Cypress).
Familiarity with LangGraph or other orchestration frameworks is a plus.
Understanding of prompt engineering and evaluation techniques.
Ability to build modular, production-ready pipelines that integrate with developer workflows.
Nice to Have:
Experience with LangSmith or similar observability/evaluation tools.
Background in software testing, QA, or DevOps.
Familiarity with containerization (Docker) and CI/CD systems (GitHub Actions, GitLab CI, Jenkins).
Project Scope:
Initial milestone: Build a working prototype workflow (Requirements → Scenarios → Test Code → Execution → Report).
Potential for long-term collaboration to refine, extend, and productioniz
This role involves turning client requirements into automated test scenarios, generating and executing test code, and designing feedback/reporting loops that keep the workflow scalable, accurate, and reliable.
Responsibilities:
Design and build LLM-powered workflows that translate requirements into test scenarios and automation scripts.
Implement RAG pipelines for contextual test case generation and knowledge retrieval.
Integrate workflows with automation tools (e.g., Playwright, Selenium, or similar frameworks).
Set up pipelines for test execution, results analysis, and reporting.
Collaborate on refining prompt engineering, evaluation, and optimization for accuracy and reliability.
Ensure workflows can be extended and integrated into CI/CD environments.
Required Skills:
Strong background in Python (LangChain, LlamaIndex, or similar frameworks).
Experience with LLMs (OpenAI, Anthropic, or local models like Llama/Mistral).
Knowledge of RAG architectures (vector databases such as Pinecone, Weaviate, FAISS, or Milvus).
Experience with test automation frameworks (Playwright, Selenium, or Cypress).
Familiarity with LangGraph or other orchestration frameworks is a plus.
Understanding of prompt engineering and evaluation techniques.
Ability to build modular, production-ready pipelines that integrate with developer workflows.
Nice to Have:
Experience with LangSmith or similar observability/evaluation tools.
Background in software testing, QA, or DevOps.
Familiarity with containerization (Docker) and CI/CD systems (GitHub Actions, GitLab CI, Jenkins).
Project Scope:
Initial milestone: Build a working prototype workflow (Requirements → Scenarios → Test Code → Execution → Report).
Potential for long-term collaboration to refine, extend, and productioniz