← Back to Careers
DevelopmentFull-time
AI / ML Engineer
Multan, Pakistan Full-time
Build production LLM applications, RAG pipelines and AI automation workflows for clients across four regions — with evals, guardrails and observability baked in.
What you'll do
- Design and ship LLM applications using GPT-4o, Claude and Llama — with RAG, fine-tuning and tool-using agents.
- Build evaluation harnesses with golden datasets and regression tests.
- Implement guardrails (PII, toxicity, groundedness) and cost/latency controls.
- Work with the engineering team to integrate AI into Next.js applications.
- Stay current with the LLM research literature and apply findings to client work.
What we're looking for
- 3+ years building production ML/LLM systems.
- Python (FastAPI), LangChain/LlamaIndex, pgvector/Pinecone, LangSmith/Langfuse.
- Experience with RAG, fine-tuning and agent architectures.
- Strong communication skills for client-facing workshops.
Nice to have
- Published research in NLP/ML.
- Experience with computer vision (YOLO, OCR).
- Familiarity with edge deployment (Modal, Ray).