Role overview
Lead the prompt engineering practice for an AI-powered Automated Quality Management product within a cloud contact center platform. As the founding senior hire, you will set technical standards, mentor a small engineering team, and serve as the lead authority on AI-driven evaluation design for enterprise customers. The role blends hands‑on prompt design with practice leadership, complex customer engagements, and pre‑sales support.
Responsibilities
- Define and own the prompt engineering methodology, quality gates, and best practice documentation for the team.
- Build and maintain a curated library of reusable, validated evaluation templates spanning key verticals and QM use cases.
- Mentor a team of roughly three prompt engineers through design reviews, structured feedback, and continuous improvement.
- Lead prompt engineering on the most complex, high-value customer engagements, from initial scoping through production deployment.
- Serve as the senior escalation point for prompt performance issues, failure analysis, and remediation on live deployments.
- Act as the subject matter expert in pre‑sales engagements and contribute structured product feedback to the engineering organization based on field experience.
Requirements
- Formal prompt engineering certification such as DeepLearning.AI, Anthropic, OpenAI, DAIR.AI, or an equivalent industry-recognized program.
- Advanced hands‑on experience with leading LLM platforms (OpenAI GPT-4+, Anthropic Claude, Google Gemini, Meta Llama, or similar), covering API usage, system prompt design, and evaluation harness development.
- Background in Quality Management design, including evaluation frameworks, scorecard design, calibration processes, and governance.
- Prior hands‑on experience with an AI-native QM solution such as NICE Enlighten QM, Genesys Cloud AI Quality, Medallia, Qualtrics, or comparable platforms.
- Demonstrated understanding of LLM behavior, including how prompt structure, instruction framing, persona assignment, chain-of-thought, and few‑shot examples shape outputs.
- Proven ability to translate complex business requirements into structured, testable, and scalable technical solutions, with strong written and verbal communication for senior client stakeholders.
Nice to have
- Experience owning or contributing to a Speech Analytics or QM center of excellence, including methodology documentation and internal training.
- Familiarity with prompt evaluation frameworks such as LLM-as-judge or human-in-the-loop evaluation pipelines.
- Exposure to NLP concepts like tokenization, embeddings, and semantic similarity sufficient to reason about prompt performance.
- Comfort with JSON, Python scripting, or no-code automation tools applied to prompt testing and workflow automation.
- Background in compliance-driven contact center QM environments (financial services, healthcare, utilities) where regulatory accuracy adds constraints.
Benefits and work setup
- Fully remote for candidates outside a 30-mile office radius; hybrid schedule of three in-office days per week for those within range.
- US base salary range of $88,900–$247,700, with potential annual performance bonus, equity, and other incentive plans.
- Health, dental, and vision coverage starting day one, with employee premiums fully covered and shared dependent costs.
- Short- and long-term disability, basic life insurance, and a 401(k) plan with employer matching.
- Mental health support platform, employee stock purchase plan, paid time off, company-paid holidays, paid volunteer hours, and 12 weeks of paid parental leave.