AI Engineer

AI Engineer (LLM & Voice Pipeline)

Company: Uplers (for ADNA client)

Location: Pune, India

Opportunity Type: Remote

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

Experience Required: 2+ years

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

Notice Period: 15 Days

About the Role:

ADNA is seeking an AI Engineer to manage and enhance their AI systems, focusing on scalability and continuous improvement. You will be instrumental in ensuring the AI brains behind their operations perform optimally.

Responsibilities:

• Oversee the end-to-end AI pipeline orchestration, including Speech-to-Text (STT), Large Language Models (LLMs), and Text-to-Speech (TTS).
• Implement and monitor prompt flows, sophisticated fallback strategies, and robust recovery logic.
• Measure and enhance conversational quality, focusing on metrics such as latency, hallucination rates, success rates, and barge-in capabilities.
• Develop comprehensive test sets, conduct A/B experiments, and proactively identify regressions before they impact users.
• Collaborate closely with the Tech Lead and Voice UX designer to ensure model behavior aligns with real-world conversational nuances.

Must-Have Skills:

• Proficient Python skills and experience integrating with LLM APIs (e.g., OpenAI, Anthropic, Azure).
• Proven experience shipping or maintaining LLM-powered products in production.
• Familiarity with STT/TTS tools such as Whisper, ElevenLabs, Coqui, Google, and Azure.
• Expertise in prompt engineering, context control, session state management, and fallback orchestration.
• Ability to effectively log, trace, and debug model behavior, treating it akin to backend logic.

Bonus Points:

• Experience with evaluation tools like Langfuse, TruLens, Helix, Ragas, or building 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.
• Managed golden sets, live traffic shadowing, or prompt regression testing.

What You Will Gain:

• Direct ownership of AI behavior and quality across the entire product lifecycle.
• A collaborative team environment that values pragmatism, iteration, and clean architecture.
• Significant input into the personality, intelligence, and adaptability of AI agents.
• The opportunity to shape an AI system that directly interacts with users and is evaluated on its conversational performance.

This Role is NOT For:

• Individuals seeking prompt monkey work or basic QA tasks.
• Those interested in training foundation models or fine-tuning LLMs from scratch.
• Research-focused positions.

This position is ideal for someone passionate about deploying robust LLM-powered voice agents that perform reliably under real-world demand and continuously improve over time.

How to Apply:

1. Click 'Apply' and Register/Login on the Uplers portal.
2. Complete the screening form and upload your updated resume.
3. Increase your chances by preparing for the client interview.