AI Engineer

We are seeking an experienced AI Engineer specializing in Large Language Models (LLMs) and Voice Pipelines to join our client, ADNA. In this role, you will be instrumental in ensuring our AI systems function seamlessly, scale effectively, and continuously improve. Your responsibilities will encompass the entire AI pipeline, from Speech-to-Text (STT) to LLM processing and Text-to-Speech (TTS) output. You will implement and monitor prompt flows, develop fallback strategies, and implement recovery logic to maintain optimal performance. A key part of your role will involve measuring and enhancing conversational quality by focusing on latency, hallucination rates, success rates, and barge-in detection. You will be responsible for building robust test sets, conducting A/B experiments, and proactively identifying regressions before they impact users. Collaboration with the Tech Lead and Voice UX designer will be crucial to align model behavior with real-world conversational nuances.

Requirements

• Proficient in Python with experience integrating with LLM APIs such as OpenAI and Anthropic.
• Proven track record of shipping or maintaining products that utilize LLMs in production environments.
• Familiarity with STT/TTS tools including Whisper, ElevenLabs, Coqui, Google, and Azure.
• Experience in prompt engineering, context control, session state management, and fallback orchestration.
• Skilled in logging, tracing, and debugging model behavior analogous to backend logic.

Bonus Points

• Experience with evaluation tools like Langfuse, TruLens, Helix, or Ragas, or the ability to build custom evaluation tooling.
• Worked with latency-sensitive systems, including real-time or streaming pipelines.
• Experience setting up CI for prompt evaluation or contributing to LLMOps pipelines.
• Proficiency in managing golden sets, live traffic shadowing, or prompt regression testing.

What You'll Get

• Significant ownership over AI behavior and quality across the entire product.
• A collaborative team environment that values pragmatism, iterative development, and clean architecture.
• Opportunity to influence the voice, intelligence, and adaptability of our AI agents.
• The chance to shape an AI system that directly interacts with users and is evaluated on its conversational performance.

This Role Is NOT For You If

• You are looking for a role focused solely on prompt refinement or basic QA tasks.
• Your interest lies in training foundation models or tuning large language models from scratch.
• You are seeking a pure research position.

This opportunity is ideal for individuals passionate about deploying robust, LLM-powered voice agents that perform reliably under real-world conditions and demonstrate continuous improvement.

Location: Delhi, India (Remote)

Experience Required: 2+ years

Notice Period: 15 Days

Shift: (GMT+04:00) Asia/Dubai (GST)

Opportunity Type: Remote

Placement Type: Full Time Permanent (Payroll and Compliance managed by ADNA)