Senior AI Engineer

Location | DHA6, Lahore
Experience | 3 - 5 Year

We are seeking an AI Engineer with 3–5 years of experience to build and deploy Generative AI systems, with a strong focus on AI agents, multi-agent workflows, and RAG-based applications. This role is hands-on and production-oriented, working with modern GenAI frameworks, automation tools, and cloud platforms.

Key Responsibilities

• Design and build LLM-powered applications, including chatbots, copilots, and internal AI tools.
• Develop AI agents and multi-agent systems for task automation, reasoning, and tool orchestration.
• Implement and optimise RAG pipelines, prompt engineering, and context management.
• Fine-tune and adapt foundation models for domain-specific use cases. Build and deploy AI services using FastAPI/Flask, Docker, and cloud platforms.
• Apply computer vision techniques (OCR, detection, tracking) where required. Monitor deployed models for performance, reliability, and cost.

Required Skills & Experience

• Experience: 3–5 years in AI/ML or related engineering roles. Programming: Strong Python; working knowledge of SQL.
• Generative AI: LLMs (OpenAI, Anthropic, Gemini, open-source models), agents, multi-agent workflows, RAG. Frameworks: PyTorch, Hugging Face, LangChain, LlamaIndex.
• Automation & Orchestration: n8n or similar tools. Databases: SQL and vector databases (Pinecone, Weaviate, Milvus, FAISS).
• Deployment & MLOps: FastAPI/Flask, Docker; familiarity with MLflow is a plus. Cloud: AWS (Bedrock, SageMaker), Azure AI.

Job Type: Full-time

Work Location: Hybrid remote in Lahore