{"id":98277,"date":"2026-06-20T12:39:23","date_gmt":"2026-06-20T12:39:23","guid":{"rendered":"https:\/\/jobs.dataaxisnode.com\/kenya\/uncategorized\/prompt-engineer\/"},"modified":"2026-06-20T12:39:23","modified_gmt":"2026-06-20T12:39:23","slug":"prompt-engineer","status":"publish","type":"post","link":"https:\/\/jobs.dataaxisnode.com\/kenya\/jobs\/nairobi\/prompt-engineer\/","title":{"rendered":"Prompt Engineer"},"content":{"rendered":"<p><script type=\"application\/ld+json\">{\"@context\": \"https:\/\/schema.org\/\", \"@type\": \"JobPosting\", \"title\": \"Prompt Engineer\", \"description\": \"Key Roles and Responsibilities\\nDesign, author, and maintain production-grade prompts for AI voice bots deployed across outbound debt collections campaigns and inbound collections IVR in English and Swahili.\\nOptimise prompt structure using Markdown formatting principles headers, delimiters, instruction hierarchy to maximise model comprehension and minimise token overhead and call latency.\\nTune 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.\\nEvaluate how prompt length, token count, instruction complexity, and model parameters temperature, max_tokens, streaming affect inference latency and per-call cost.\\nImplement 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.\\nConduct structured QA audits on sampled collections call recordings, scoring against defined parameters script adherence, tone, promise-to-pay handling, loan disclosure compliance.\\nMaintain a versioned prompt change log with A\/B test configurations and measurable outcome data; produce regular performance summaries for the Call Center Manager.\\nCoordinate with the DC IT Technical Support Officer on API configurations, Webitel IVR routing, SIP trunk settings, and system-level constraints that affect prompt deployment.\\nCollaborate with collections strategy teams to translate DPD bucket cadence rules and product-specific scripts Boda, Tuk-Tuk, smartphone loans into accurate bot logic.\\nLiaise with AI vendors\u00a0on ASR quality, voice synthesis settings, and integration constraints relevant to Kenya collections operations.\\nMonitor per-call cost metrics and propose prompt changes that improve recovery rates and ROI without compromising quality or compliance.\\nAny other duties that may be assigned.\\nExperience\\nMinimum 1\u20132 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.\\nDemonstrated experience designing and deploying prompts or dialogue flows for production LLM or voice-bot systems \u2014 not solely experimental or academic work.\\nTrack record of tuning and evaluating prompts against measurable KPIs and running structured A\/B tests to improve real-world outcomes.\\nPrior exposure to contact-centre, telephony, or IVR environments, ideally in collections, customer service, or financial services.\\nExperience in or alongside debt collections, lending, fintech, BPO, or banking operations is a strong advantage.\\nExperience collaborating with cross-functional teams IT, strategy, operations and managing third-party AI \/ voice-vendor relationships is desirable.\\nExperience producing English- and Swahili-language conversational content for a Kenyan or East African customer base is highly desirable.\\nQualifications\\nEducation & Certifications:\\nBachelor'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.\\nA reviewable portfolio of production prompt work \u2014 prompt libraries, system prompts, evaluation harnesses, or published repositories \u2014 that can be walked through at interview.\\nCertification in Google Cloud Vertex AI \/ Generative AI, OpenAI, or an equivalent LLM \/ conversational-AI program is an added advantage.\\nTechnical Skills:\\nHands-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.\\nWorking proficiency with at least one major LLM platform \u2014 Google Gemini AI Studio \/ Vertex AI and\/or OpenAI GPT-4o \u2014 including parameter tuning temperature, max_tokens, top-p, streaming and a practical grasp of tokenization and context-window economics.\\nUnderstanding of voice-AI pipelines \u2014 automatic speech recognition ASR and text-to-speech TTS \u2014 and how transcription accuracy, latency, and barge-in behaviour affect live call performance.\\nFamiliarity with IVR \/ telephony concepts: Webitel or comparable contact-centre platforms, SIP trunking, call routing, and API-based integrations.\\nAbility 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.\\nCompetence in designing and interpreting A\/B tests and quantitative metrics \u2014 latency, containment, promise-to-pay rate, recovery rate, and cost-per-call.\\nLanguage & Domain Knowledge:\\nFull professional fluency in English and Swahili, with the ability to author, review, and QA bot dialogue and call scripts in both languages.\\nAwareness of debt-collections conduct stand\", \"datePosted\": \"2026-06-19\", \"hiringOrganization\": {\"@type\": \"Organization\", \"name\": \"Mogo Finance\"}, \"jobLocation\": {\"@type\": \"Place\", \"address\": {\"@type\": \"PostalAddress\", \"addressLocality\": \"Nairobi\", \"addressCountry\": \"KE\"}}, \"directApply\": true, \"validThrough\": \"2026-07-15T23:59:59\", \"employmentType\": \"FULL_TIME\"}<\/script><\/p>\n<p><strong>Company:<\/strong> Mogo Finance<\/p>\n<p><strong>Location:<\/strong> Nairobi<\/p>\n<p><strong>Job Type:<\/strong> Full Time<\/p>\n<p><strong>Apply Before:<\/strong> 2026-07-15<\/p>\n<h3>Job Description<\/h3>\n<p>Key Roles and Responsibilities<br \/>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.<br \/>Optimise prompt structure using Markdown formatting principles headers, delimiters, instruction hierarchy to maximise model comprehension and minimise token overhead and call latency.<br \/>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.<br \/>Evaluate how prompt length, token count, instruction complexity, and model parameters temperature, max_tokens, streaming affect inference latency and per-call cost.<br \/>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.<br \/>Conduct structured QA audits on sampled collections call recordings, scoring against defined parameters script adherence, tone, promise-to-pay handling, loan disclosure compliance.<br \/>Maintain a versioned prompt change log with A\/B test configurations and measurable outcome data; produce regular performance summaries for the Call Center Manager.<br \/>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.<br \/>Collaborate with collections strategy teams to translate DPD bucket cadence rules and product-specific scripts Boda, Tuk-Tuk, smartphone loans into accurate bot logic.<br \/>Liaise with AI vendors\u00a0on ASR quality, voice synthesis settings, and integration constraints relevant to Kenya collections operations.<br \/>Monitor per-call cost metrics and propose prompt changes that improve recovery rates and ROI without compromising quality or compliance.<br \/>Any other duties that may be assigned.<br \/>Experience<br \/>Minimum 1\u20132 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.<br \/>Demonstrated experience designing and deploying prompts or dialogue flows for production LLM or voice-bot systems \u2014 not solely experimental or academic work.<br \/>Track record of tuning and evaluating prompts against measurable KPIs and running structured A\/B tests to improve real-world outcomes.<br \/>Prior exposure to contact-centre, telephony, or IVR environments, ideally in collections, customer service, or financial services.<br \/>Experience in or alongside debt collections, lending, fintech, BPO, or banking operations is a strong advantage.<br \/>Experience collaborating with cross-functional teams IT, strategy, operations and managing third-party AI \/ voice-vendor relationships is desirable.<br \/>Experience producing English- and Swahili-language conversational content for a Kenyan or East African customer base is highly desirable.<br \/>Qualifications<br \/>Education &#038; Certifications:<br \/>Bachelor&#8217;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.<br \/>A reviewable portfolio of production prompt work \u2014 prompt libraries, system prompts, evaluation harnesses, or published repositories \u2014 that can be walked through at interview.<br \/>Certification in Google Cloud Vertex AI \/ Generative AI, OpenAI, or an equivalent LLM \/ conversational-AI program is an added advantage.<br \/>Technical Skills:<br \/>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.<br \/>Working proficiency with at least one major LLM platform \u2014 Google Gemini AI Studio \/ Vertex AI and\/or OpenAI GPT-4o \u2014 including parameter tuning temperature, max_tokens, top-p, streaming and a practical grasp of tokenization and context-window economics.<br \/>Understanding of voice-AI pipelines \u2014 automatic speech recognition ASR and text-to-speech TTS \u2014 and how transcription accuracy, latency, and barge-in behaviour affect live call performance.<br \/>Familiarity with IVR \/ telephony concepts: Webitel or comparable contact-centre platforms, SIP trunking, call routing, and API-based integrations.<br \/>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.<br \/>Competence in designing and interpreting A\/B tests and quantitative metrics \u2014 latency, containment, promise-to-pay rate, recovery rate, and cost-per-call.<br \/>Language &#038; Domain Knowledge:<br \/>Full professional fluency in English and Swahili, with the ability to author, review, and QA bot dialogue and call scripts in both languages.<br \/>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.<br \/>Personal Attributes:<br \/>Strong analytical and problem-solving mindset with meticulous attention to detail.<br \/>Comfortable with ambiguous requirements and rapid, data-driven iteration.<br \/>Clear written and verbal communicator who can translate technical findings for non-technical stakeholders.<br \/>Self-driven and organised, able to maintain a versioned change log across multiple concurrent campaigns.<br \/>With us you will:<br \/>Feel Good<br \/>a competitive salary<br \/>a friendly and dynamic work environment<br \/>an excellent well-being program:<br \/>health insurance after probation period<br \/>pension scheme after probation period<br \/>active social life and events<br \/>Win<br \/>Fast results without the friction of bureaucracy<br \/>great victories due to the transparency of the company and its goals<br \/>bonuses and awards for the great work<br \/>participate in victory celebrations with your co-workers<br \/>Grow<br \/>together with an intelligent team<br \/>yourself and the company with the established feedback culture<br \/>your knowledge with training possibilities<\/p>\n<h3>How to Apply<\/h3>\n<p>Interested and qualified? Go to Mogo Finance on talent.sage.hr to apply<br \/>Build your CV for free. Download in different templates.<\/p>\n<p><a href=\"https:\/\/www.myjobmag.co.ke\/apply-now\/1256605\" target=\"_blank\" rel=\"noopener\" style=\"display:inline-block;padding:10px 20px;background:#2271b1;color:#fff;text-decoration:none;border-radius:4px;\">Apply Now<\/a><\/p>\n<p><small>Source: MyJobMag<\/small><\/p>\n<p><!-- job-expiry: 2026-07-15 --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Company: Mogo Finance Location: Nairobi Job Type: Full Time Apply Before: 2026-07-15 Job Description Key Roles and ResponsibilitiesDesign, 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 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[1408,1409],"tags":[1425,1413,1515,1412],"class_list":["post-98277","post","type-post","status-publish","format-standard","hentry","category-jobs","category-nairobi","tag-full-time","tag-job-listing","tag-mogo-finance","tag-myjobmag"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/posts\/98277","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/comments?post=98277"}],"version-history":[{"count":0,"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/posts\/98277\/revisions"}],"wp:attachment":[{"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/media?parent=98277"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/categories?post=98277"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jobs.dataaxisnode.com\/kenya\/wp-json\/wp\/v2\/tags?post=98277"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}