We are seeking a Senior AI Engineer to design and build scalable AI solutions with a strong focus on Agentic AI, RAG systems, and production-grade LLM applications.The role emphasizes hands-on development, practical system design, and reliable production deployment, along with structured evaluation and observability practices

Responsibilities : 

• Design and implement RAG-based AI systems with hybrid search, embeddings, and optimized retrieval strategies
• Build and deploy AI agents using modern agentic AI frameworks
• Develop multi-step workflows and tool-using agents for real-world business use cases
• Build conversational AI systems with context handling and multi-turn interactions
• Design scalable AI services for real-time and batch use cases
• Design and implement solutions using at least one of the following frameworks:
  • LangGraph
  • Semantic Kernel
  • AutoGen
  • CrewAI
  • OpenAI Agents SDK
• Demonstrate working knowledge of multiple agent frameworks and their trade-offs
• Apply prompt engineering, few-shot learning, and retrieval techniques to improve LLM performance
• Build reusable components for agent orchestration, tool usage, and workflow design
• Design and implement semantic search and vector-based retrieval systems
• Hands-on experience with:
  • Azure AI Search
  • PostgreSQL (pgvector)
• Optimize embedding strategies, indexing, and query performance
• Implement LLM evaluation approaches (offline testing, basic automated evaluation pipelines)
• Define and track quality metrics such as accuracy, relevance, and response quality
• Apply techniques for hallucination detection and mitigation
• Build basic monitoring and observability for AI systems (logs, traces, performance metrics)
• Continuously improve model performance based on evaluation insights
• Develop APIs and microservices for integrating AI systems
• Work with cloud platforms (Azure/AWS/GCP) and containerization (Docker)
• Contribute to deployment pipelines and production readiness
• Prototype and validate solutions through POCs and pilots

Requirements :

• 6–9 years of experience in AI/ML
• Strong Python skills and experience with ML frameworks (PyTorch or TensorFlow)
• Practical experience building LLM-based applications and RAG pipelines
• Hands-on experience with at least one agentic AI framework:
  • LangGraph, Semantic Kernel, AutoGen, CrewAI, or OpenAI Agents SDK
• Familiarity with multi-agent workflows and orchestration patterns
• Experience with vector databases and semantic search systems
• Hands-on exposure to:
  • Azure AI Search
  • pgvector (PostgreSQL)
• Understanding of embeddings and similarity search
• Experience or strong understanding of:
  • LLM evaluation techniques
  • Output quality measurement
  • Hallucination detection approaches
  • Monitoring and observability concepts
• Agentic AI: LangGraph, Semantic Kernel, AutoGen, CrewAI, OpenAI Agents SDK
• RAG Frameworks: LangChain, LlamaIndex
• Vector Databases: Azure AI Search, pgvector
• LLM/ML: PyTorch, OpenAI APIs
• Serving: FastAPI
• Infra: Azure/AWS/GCP, Docker
• Monitoring: LangSmith (or similar)
• Languages: Python

We have an amazing team of 700+ individuals working on highly innovative enterprise projects & products. Our customer base includes Fortune 100 retail and CPG companies, leading store chains, fast-growth fintech, and multiple Silicon Valley startups.

What makes Confiz stand out is our focus on processes and culture. Confiz is ISO 9001:2015 (QMS), ISO 27001:2022 (ISMS), ISO 20000-1:2018 (ITSM) and ISO 14001:2015 (EMS) Certified. We have a vibrant culture of learning via collaboration and making workplace fun.

People who work with us work with cutting-edge technologies while contributing success to the company as well as to themselves. 

To know more about Confiz Limited, visit: https://www.linkedin.com/company/confiz-pakistan/