LLM AI Engineer: Agents & RAG with FastAPI

taraki-search; Lahore; On-site; PKR 2,400,000 - 6,000,000; Full time

Job summary

Exper Labs in Lahore seeks an AI Engineer with 3–6 years of software experience to build AI agents using LLMs and RAG. You will design prompts, integrate major LLM APIs, and develop FastAPI microservices that orchestrate agent workflows in a containerized environment.

You will work with Pinecone/FAISS for context-aware interactions, apply prompt engineering, and contribute to in-house model training and optimization initiatives as the platform evolves.

Qualifications

• 3–6 years of hands-on software engineering in AI/ML systems.
• Experience integrating external LLMs (OpenAI, Anthropic, Google).
• Strong prompts design and effective LLM interactions.
• Proficiency with Python and FastAPI for RESTful APIs.
• Experience with RAG implementations and vector databases.
• Cloud familiarity (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).
• Foundational ML knowledge; exposure to PyTorch, TensorFlow, or Hugging Face.
• Strong problem solving, communication, and Agile teamwork.
• Bachelor's or Master's in Computer Science, AI, or related.

Responsibilities

• Architect, build, test, and maintain AI agents in FastAPI services.
• Integrate with LLM APIs; design prompts for retail use cases.
• Implement RAG with vector databases to enrich interactions.
• Develop scalable microservices to manage agent logic and LLMs.
• Prepare data for prompt context and potential model fine-tuning.
• Collaborate with product and engineering teams on AI features.

Skills

Python

FastAPI

LLM integration

Prompt engineering

RAG

Docker

Kubernetes

Cloud platforms

Agile

Education

Bachelor's or Master's in CS/AI

Tools

Pinecone

FAISS

PyTorch

TensorFlow

Hugging Face

Job description

Exper Labs in Lahore seeks an AI Engineer with 3–6 years of software experience to build AI agents using LLMs and RAG. You will design prompts, integrate major LLM APIs, and develop FastAPI microservices that orchestrate agent workflows in a containerized environment.

You will work with Pinecone/FAISS for context-aware interactions, apply prompt engineering, and contribute to in-house model training and optimization initiatives as the platform evolves.