Prompt Engineer

MOGO Auto Limited is part of Eleving Group, an international fintech company operating in sixteen countries across three continents. We are a world-class, reliable, and internationally trusted partner, expanding access to finance in Kenya to promote upward social mobility. Our portfolio encompasses a range of financial products, including car financing, motorcycle financing, tuk-tuk financing, electric motorcycle financing, logbook loans, and vehicle financing.

Since entering the Kenyan market in 2019, we have financed over 100,000 vehicles and served over 50,000 satisfied customers. In June 2024, our new motorcycle financing issuances surpassed the 230 million Kenya shilling mark. 

Our growth is attributed to a focused market growth strategy, a strong emphasis on data and technology, and robust risk management structures. We process loan requests within 24 hours and offer flexible repayment terms of up to 60 months.

Our mission is to provide convenient and affordable financing solutions to our customers, backed by a lowest price guarantee. 

MOGO is one of the few financial companies globally that finances cars of any age, brand, or model. We empower our customers to choose vehicles from trusted dealerships through our user-friendly online car portal. 

Mogo Auto Limited recently signed a commitment letter with Development Finance Corporation (DFC), for a $10 million loan to finance electric vehicles in Kenya. 

Our goal is to facilitate upward social mobility across Kenyan communities by providing innovative and sustainable financial solutions. We strive to build mutually beneficial partnerships with our customers, helping them find the best deals and guiding them through the purchasing process. 

Join us - you'll love working in a collaborative and non-bureaucratic environment that is fun yet stable and sustainable.

• 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. 

• 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 structured A/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. 

Education & Certifications: 

• 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. 
• 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. 

Technical Skills: 

• Hands-on command of core prompt-engineering techniques: system and role prompting, few-shot and chain-of-thought design, delimiter and Markdown structuring, output schema and constraint control, and guardrail / fallback design. 
• Working proficiency with at least one major LLM platform — Google Gemini (AI Studio / Vertex AI) and/or OpenAI GPT-4o — including parameter tuning (temperature, max_tokens, top-p, streaming) and a practical grasp of tokenization and context-window economics. 
• Understanding of voice-AI pipelines — automatic speech recognition (ASR) and text-to-speech (TTS) — and how transcription accuracy, latency, and barge-in behaviour affect live call performance. 
• Familiarity with IVR / telephony concepts: Webitel or comparable contact-centre platforms, SIP trunking, call routing, and API-based integrations. 
• Ability to read and reason about JSON API request/response payloads and to work in API consoles (e.g., Postman). Basic scripting in Python or JavaScript for prompt testing and batch evaluation is an advantage. 
• Competence in designing and interpreting A/B tests and quantitative metrics — latency, containment, promise-to-pay rate, recovery rate, and cost-per-call. 

Language & Domain Knowledge: 

• Full professional fluency in English and Swahili, with the ability to author, review, and QA bot dialogue and call scripts in both languages. 
• Awareness of debt-collections conduct standards and Kenyan consumer-protection and data-privacy obligations, including the Data Protection Act, 2019 and CBK consumer-protection expectations. 

Personal Attributes: 

• Strong analytical and problem-solving mindset with meticulous attention to detail. 
• Comfortable with ambiguous requirements and rapid, data-driven iteration. 
• Clear written and verbal communicator who can translate technical findings for non-technical stakeholders. 
• Self-driven and organised, able to maintain a versioned change log across multiple concurrent campaigns. 

Feel Good

• a competitive salary
• a friendly and dynamic work environment
• an excellent well-being program:
• health insurance (after probation period)
• pension scheme (after probation period)
• active social life and events

Win

• Fast results without the friction of bureaucracy
• great victories due to the transparency of the company and its goals
• bonuses and awards for the great work
• participate in victory celebrations with your co-workers

Grow

• together with an intelligent team
• yourself and the company with the established feedback culture
• your knowledge with training possibilities