Pakistan onlyWe’re looking for a hands-on Principal Engineer (AI Systems) who loves to build, not just design.
You’ll spend your time writing code, experimenting with LLMs, and turning ideas into production-grade Generative AI systems. You’ll work directly on Retrieval-Augmented Generation (RAG), LLMOps, and multi-agent orchestration frameworks, solving real technical problems every day.
You’ll spend your time writing code, experimenting with LLMs, and turning ideas into production-grade Generative AI systems. You’ll work directly on Retrieval-Augmented Generation (RAG), LLMOps, and multi-agent orchestration frameworks, solving real technical problems every day.
This is a purely technical IC role, not a managerial one. You’ll lead by example, mentor through code reviews, and own end-to-end technical delivery.
Key Responsibilities
- Design and code RAG systems with embeddings, hybrid search, and evaluation pipelines.
- Develop hands-on multi-agent orchestration frameworks (LangGraph, AutoGen, CrewAI, or custom).
- Implement and maintain LLMOps pipelines for prompt versioning, cost tracking, and evaluation.
- Integrate AI workflows with backend services and data layers for real-world scalability.
- Experiment with LLMs for retrieval, summarization, and personalization use cases.
- Contribute directly to code, architecture reviews, and performance improvements.
Collaborate with data and platform engineers to deploy and optimize GenAI solutions.
Skills, Knowledge and Expertise
Must-Have Skills
- 5+ years of backend or ML engineering experience, with strong Python coding skills.
- Proven experience shipping RAG systems (vector DBs, embeddings, chunking).
- Familiarity with orchestration frameworks (LangGraph, LangChain, AutoGen, or similar).
- Understanding of LLM behavior, evaluation, and fine-tuning workflows.
- Experience with APIs, microservices, and cloud-native development (AWS preferred).
Nice-to-Have
- Experience with unstructured data (PDFs, tables, images).
- Familiarity with distributed systems concepts (async, message queues, caching).
- Experience with LLM evaluation or reinforcement learning from feedback (RLAIF).
- Understanding of data versioning or retrieval metrics.
Soft Skills
- Builder mindset — thrives on writing, debugging, and improving production code.
- Collaborative, humble, and open to feedback.
- Strong communicator who explains design decisions clearly.
Influences through contribution, not hierarchy.
United States