AI Practice
Full-time
3–7 years
AI Engineer (LLM & RAG)
Ship retrieval-augmented systems, agents and document intelligence pipelines with real evaluation harnesses behind them.
Remote (India / UAE)
What you will do
Responsibilities
- Build retrieval pipelines, evaluation sets and guardrails for production LLM systems
- Instrument quality, latency and cost metrics for every deployed model path
- Partner with domain experts to encode operational rules correctly
What we look for
Requirements
- Python plus practical experience with vector stores and embeddings
- Track record shipping LLM features that survived real users
- Rigour about evaluation, hallucination control and data privacy
Process
How hiring works for this role
Written feedback at each stage, and a decision within three weeks of your application.
- 01
Application review
We read every application. Expect a response within five working days.
- 02
Craft conversation
A 45-minute discussion about systems you have built and the trade-offs you chose.
- 03
Practical exercise
A scoped, paid or time-boxed exercise close to real work. No algorithm puzzles.
- 04
Team and offer
Meet the pod you would join, discuss compensation and receive a written offer.