Description:
We are looking for a high-impact AI Agents Developer to work onsite at our Faisalabad office, building production-ready AI agents using modern LLM frameworks and scalable backend architectures.
This role is NOT about basic chatbots.
You will design autonomous, tool-using, memory-driven, multi-agent systems that act as Digital Full-Time Equivalents (AI FTEs) for real businesses.
🔑 Key Responsibilities
- Design and develop LLM-powered AI Agents using modern agentic architectures
- Build tool-calling agents (APIs, DBs, SaaS integrations)
- Implement multi-agent workflows (planner → executor → verifier)
- Develop RAG pipelines using vector databases
- Create agents for Finance, Sales, HR, Operations, Support
- Optimize agents for cost, latency, accuracy, and safety
- Build evaluation metrics, logs, and feedback loops
- Collaborate onsite with Product Managers, Backend Engineers, and UI teams
- Convert business workflows into autonomous AI systems
- Write clean, scalable, production-ready code
🧰 Core Tech Stack (Must-Have)AI & Agent Frameworks
- OpenAI APIs (GPT-4.x, Assistants, Functions / Tools)
- OpenAI Agents SDK
- Claude Agents SDK
- Prompt Engineering & Agent Orchestration
- RAG (Retrieval-Augmented Generation)
Backend
- Python (FastAPI) – mandatory
- REST APIs, async processing
- Background workers & task queues
Databases
- PostgreSQL
- Vector DBs: Pinecone (preferred), Qdrant, Weaviate
- Redis (optional)
Frontend (Basic Understanding)
- Next.js
- TypeScript
- Tailwind CSS
Cloud & DevOps
- AWS or Azure
- Docker
- CI/CD (GitHub Actions)
- Environment-based deployments
🎓 Required Qualifications
- BS / MS in Computer Science, Software Engineering, or related field
- 6 Months+ of backend or AI engineering experience
- Hands-on experience building AI agents or LLM-based systems
- Strong command of Python & FastAPI
- Solid understanding of:
- Prompt design
- Tool calling
- Memory & context handling
- RAG architectures
- Ability to work onsite in Faisalabad