Senior Prompt Engineer (Onsite, Dubai)

Isa Cybersecurity Inc.; Dubai; On-site; AED 357,120 - 580,320; Full time

Benefits offered by this job

Work visa Provided

Housing in Dubai

Flights covered

Medical insurance

Job summary

Isa Cybersecurity Inc. seeks a senior voice AI engineer to scale a GCC flagship airline project from text to voice. You’ll embed onsite with client teams in Dubai, owning prompts, ASR/TTS quality, and guardrails across a multi-LLM stack.

You will design multilingual English/Arabic voice flows, optimize latency, and ensure safe, auditable changes in production with strong telephony knowledge.

Qualifications

• 4+ years building production conversational systems.
• Proven prompting experience with structured tool use and streaming.
• Hands-on experience with at least one ASR engine and one TTS engine.
• Knowledge of SIP and telephony basics: signaling, RTP/SRTP, DTMF, call routing.
• Experience with validation/guardrail LLM layers (hallucination checking, PII masking).
• Experience with Voice frameworks and low-latency processing.
• Production work on voice channels; Asterisk knowledge is a plus.
• Multi-agent orchestration or custom agent frameworks.
• Airline/travel terminology and phonetic handling.
• Open-source voice-agent contributions and real customer testing.

Responsibilities

• Design and iterate voice-agent prompts for a scalable LLM stack.
• Build multilingual voice flows (English/Arabic) and SSML.
• Tune multi-LLM pipeline layers for latency and accuracy.
• Drive ASR/TTS quality across providers and configurations.
• Instrument voice KPIs and run A/B experiments on prompts.
• Make prompt/rule changes safe, auditable, and reversible in production.

Skills

LLM agent prompting

ASR/TTs

Multilingual voice

Voice UX design

Telephony basics

Guardrail LLM layers

Voice frameworks

Production voice work

Open-source contributions

Tools

Azure AI Speech

Google STT

Deepgram

ElevenLabs

OpenAI Realtime

LiveKit

Vocode/Pipecat

Asterisk

Job description

About the project

Our client, a flagship airline from the GCC region, is scaling its conversational AI platform from text to voice. Text-based agents are live; the next step is a production-grade voice experience over IVR. You will be embedded onsite with the client’s AI, backend, and telephony teams as the reference person for everything spoken, backed by our voice AI platform team.

Engagement terms

• Onsite in Dubai, client office, 5 days/week (Mon–Fri)
• Initial phase: approx. 4 months (August – December)
• Possible extension into further phases (4 / 6 / 12 months) subject to contract renewal and performance, with home leave between phases
• We cover: work visa, housing, round-trip flights, medical insurance
• Overtime is possible and paid at the standard hourly equivalent
• Possible performance bonus based on client’s end-of-phase feedback ("Exceeded Expectations")

What you will do

• Design and iterate voice-agent prompts for an LLM-based conversational stack: latency, barge-in and interruption handling, turn-taking, confirmation patterns, graceful fallback to DTMF or a human agent
• Build multilingual voice flows (English and Arabic): you own the engineering side – prompt structure, SSML, custom lexicons, pronunciation handling; Arabic linguistic quality is covered by dedicated linguists and native testers
• Work within a multi-LLM pipeline — answer generation, response validation (hallucination checks), guardrails, PII masking, routing — and tune each layer without degrading latency
• Drive ASR/TTS quality: dual-STT configurations, provider selection and tuning (Azure AI Speech, Deepgram, Google, ElevenLabs, OpenAI Realtime), barge-in behavior, endpointing
• Instrument voice KPIs on the analytics dashboard — containment, task completion, success/error rate, abandonment, misrecognition on critical slots — and run A/B experiments on prompt variants
• Make prompt and rule changes safe, auditable, and reversible in production

Must have

• 4+ years building production conversational systems
• Proven LLM agent prompting experience (OpenAI, Anthropic or equivalent) with structured tool use and streaming — be ready to show a prompt library or before/after metrics
• Hands‑on experience with at least one ASR engine (Azure AI Speech, Google STT, Deepgram, Whisper) and one TTS engine (Azure, ElevenLabs, Google)
• Shipped a voice slot‑capture flow (email or name capture) and understand why it is hard
• Working knowledge of SIP and telephony basics: signaling, RTP/SRTP, DTMF modes, codecs, call routing via SIP trunk to a bot platform
• Experience with validation/guardrail LLM layers (hallucination checking, PII masking)
• LiveKit or similar low‑latency voice‑agent frameworks (Pipecat, Vocode), OpenAI Realtime API
• Hands‑on production work on the voice channel; Asterisk experience
• Multi‑agent orchestration or custom agent frameworks
• Airline/travel domain terminology (PNR, ticket numbers, airport codes) and its phonetic handling
• Open‑source voice‑agent contributions; experience running voice user‑testing with real customers

What success looks like

• Voice agent live in production in English and Arabic with a defined containment target (Arabic linguistic QA by our native testers)
• Misrecognition on the top three high-value slots (email, PNR, phone number) cut by 30%+ vs. launch baseline
• Repeatable evaluation harness so every prompt change is measured before it ships