Loading...
USM Jobs / AI Developer
High Contract

JB062012 - AI Developer Apply

  • Start Date:
    Interview Types
  • Skills GenAI / LLM + agenti..
    Visa Types Green Card, US Citiz..
Position Title: AI Developer
Location: Mclean, VA
Duration: 6-12 Months Contract

Job Description:

Required Technical Skills :
GenAI / LLM + agentic development
  • Hands-on experience building LLM-powered agents (tool-using, multi-step reasoning, guardrails).
  • Experience with prompting patterns, structured outputs (JSON schemas), evaluation, and reducing hallucinations.
  • Ability to design agent workflows for:
o   Test generation/augmentation
o   Requirements review and completeness validation
o   Report generation and summarization
GitHub platform + GHCP (Copilot) for engineering workflows
  • Strong proficiency with GitHub Copilot in day-to-day development.
  • Deep experience with GitHub platform capabilities:
Test automation engineering (framework expertise)
  • Advanced experience designing and implementing automation with:
o   Karate (API testing, contract-like checks, data-driven testing, mocks)
o   Playwright (UI automation, selectors strategy, parallelization, trace/video artifacts)


1) Agentic test automation foundation (reusable patterns + reference implementations)
·       Design and implement agentic testing patterns that can be adopted by multiple Underwriting teams (and later other domains).
·       Create reference implementations (sample repos / templates) demonstrating:
o   Test generation assistance (from requirements, APIs, contracts, schemas)
o   Test maintenance assistance (auto-updating selectors/contracts, flaky test triage)
o   Failure analysis assistance (root cause suggestions, log correlation, defect drafting)
·       Establish a standard architecture for test code organization, tagging, data management, and execution across UI + API + service layers.
2) Coverage standards, templates, and governance
  • Define and publish coverage standards (what “good” looks like) including:
o   Minimum coverage expectations by service/component
o   Test type mix (unit vs API vs UI vs contract vs integration)
o   Risk-based prioritization and traceability to requirements
  • Provide templates usable across teams:
o   Test plan templates
o   Test case/spec templates (Gherkin-style or equivalent)
o   Definition of Ready / Definition of Done quality checklists
  • Create a scalable tagging/metadata strategy (e.g., feature, service, risk, priority, data sensitivity) to support reporting and quality gates.
3) GenAI-assisted reporting and quality insights across microservices
  • Build automated reporting that aggregates test + service data across multiple microservices, such as:
o   Test execution results (Karate/Playwright + CI runs)
o   Service health signals (logs/metrics/traces if available)
o   Defect signals (issue tracker metadata if available)
  • Generate GenAI-driven summaries:
o   Release readiness narratives
o   Failure clustering and trend analysis
o   “What changed?” insights (commit/PR correlation)
  • Produce outputs consumable by engineering leadership and teams (dashboards, markdown summaries in PRs, artifacts in CI).
4) “Quality gates” via agents 
  • Build automated review agents that evaluate user stories/requirements for minimum required clarity and data before development/testing starts:
o   Required fields present (acceptance criteria, testable outcomes, data needs, dependencies)
o   Ambiguity detection and missing edge cases
o   Data/privacy considerations and environment needs
  • Integrate gates into workflow (PR checks, issue templates, GitHub Actions) to reduce churn and rework.