Overview

We are recruiting!

Our client in the microfinance industry in Kenya is seeking an innovative and technically skilled AI Prompt Engineer to lead the design and optimization of AI-powered voice bot conversations that enhance customer engagement and drive operational performance. This is an exciting opportunity to work at the intersection of generative AI, conversational design, and financial services, developing production-grade prompts that power automated debt collection interactions in both English and Swahili. Working closely with technology, operations, and collections teams, you will continuously refine AI performance through testing, analytics, and experimentation while ensuring regulatory compliance and an exceptional customer experience. If you have hands-on experience with large language models, conversational AI, and a passion for solving real-world business challenges using AI, this role offers the opportunity to make a measurable impact in a fast-paced, technology-driven environment.

For more information and how to apply, please follow the link below.

Responsibilities

  • Design, author, and maintain production-grade prompts for AI voice bots deployed across outbound debt collections campaigns and inbound collections IVR in English and Swahili.
  • Optimise prompt structure using Markdown formatting principles (headers, delimiters, instruction hierarchy) to maximise model comprehension and minimise token overhead and call latency.
  • Tune and test prompts on Gemini 2.5 Flash (Google AI Studio / Vertex AI) and OpenAI GPT-4o, benchmarking outputs against latency, coherence, and collections compliance targets.
  • Evaluate how prompt length, token count, instruction complexity, and model parameters (temperature, max tokens, streaming) affect inference latency and per-call cost.
  • Implement and iterate on system prompts, few-shot examples, persona definitions, objection handling branches, promise-to-pay capture logic, and fallback scripts for edge-case scenarios.
  • Conduct structured QA audits on sampled collections call recordings, scoring against defined parameters (script adherence, tone, promise-to-pay handling, loan disclosure compliance).
  • Maintain a versioned prompt change log with A/B test configurations and measurable outcome data; produce regular performance summaries for the Call Center Manager.
  • Coordinate with the DC IT Technical Support Officer on API configurations, Webitel IVR routing, SIP trunk settings, and system-level constraints that affect prompt deployment.
  • Collaborate with collections strategy teams to translate DPD bucket cadence rules and product specific scripts (Boda, Tuk-Tuk, smartphone loans) into accurate bot logic.
  • Liaise with AI vendors on ASR quality, voice synthesis settings, and integration constraints relevant to Kenya collections operations.
  • Monitor per-call cost metrics and propose prompt changes that improve recovery rates and ROI without compromising quality or compliance.
  • Any other duties that may be assigned.

Qualifications

  • Bachelor’s degree in Computer Science, Software Engineering, Computational Linguistics, Data Science, or a related field. Equivalent, demonstrable hands-on experience in prompt engineering or conversational AI will be considered in lieu of a degree.
  • Minimum 1–2 years of hands-on experience in prompt engineering, conversational-AI / chatbot design, NLP, or a closely related role. Candidates with strong, demonstrable project work and shorter formal tenure may be considered.
  • Demonstrated experience designing and deploying prompts or dialogue flows for production LLM or voice-bot systems — not solely experimental or academic work.
  • Track record of tuning and evaluating prompts against measurable KPIs and running structuredA/B tests to improve real-world outcomes.
  • Prior exposure to contact-centre, telephony, or IVR environments, ideally in collections, customer service, or financial services.
  • Experience in or alongside debt collections, lending, fintech, BPO, or banking operations is a strong advantage.
  • Experience collaborating with cross-functional teams (IT, strategy, operations) and managing third party AI / voice-vendor relationships is desirable.
  • Experience producing English- and Swahili-language conversational content for a Kenyan or East African customer base is highly desirable.
  • A reviewable portfolio of production prompt work — prompt libraries, system prompts, evaluation harnesses, or published repositories — that can be walked through at interview.
  • Certification in Google Cloud (Vertex AI / Generative AI), OpenAI, or an equivalent LLM / conversational-AI program is an added advantage

Qualified candidates are welcome to apply. Please be advised that only shortlisted candidates will be contacted