Ai Engineer
Anwarson
Published Date: • Karachi, Pakistan (Hybrid)
Description
Anwarson is a technology venture committed to developing intelligent, AI-powered software solutions that combine modern AI technologies with practical business applications. We seek a skilled AI Engineer specializing in Large Language Models (LLMs) systems and integration to join our fully remote team. The successful candidate will design, develop, and integrate flexible AI architectures that support multiple AI service providers and create scalable, secure, and efficient AI-powered workflows. This position requires a minimum of two years of experience in backend development with strong proficiency in Python, along with practical knowledge of LLM APIs and AI application development. While this role does not include managing a team, the engineer will work collaboratively in a remote environment, contributing to the architecture, implementation, and continuous enhancement of AI technology infrastructure at Anwarson.
Responsibilities
Design and develop an orchestration layer that connects applications to a variety of large language models, ensuring seamless integration and flexibility across multiple AI providers including OpenAI, Google Gemini, Anthropic Claude, and Meta Llama.
Create a provider-independent AI architecture to eliminate reliance on any single AI platform, facilitating multi-model workflows that cover content generation, verification, evaluation, and continuous quality improvement. Implement advanced AI technologies such as Retrieval-Augmented Generation (RAG), embeddings, vector databases, and document-based knowledge retrieval to enhance AI system performance and accuracy.
Develop and maintain AI agents, tool-calling workflows, and structured-output pipelines to deliver robust and adaptable AI-powered services. Build and integrate APIs, backend services, and data-processing pipelines essential for AI model deployment, routing, caching, fallback mechanisms, and token cost optimization.
Establish rigorous testing and evaluation procedures to monitor AI system accuracy, latency, security, and reliability. Deploy, monitor, and maintain AI services in a production environment while collaborating with remote team members to refine technical architecture and implement ongoing improvements.
Continuously optimize system design to ensure modularity, maintainability, scalability, and high performance. Troubleshoot and solve complex technical issues independently, adhering to best practices in secure AI deployment and performance tuning.
Experience
2 Years
Apply By
Required Skills
- Data Preprocessing
- Modular system design
- Performance optimization
- Security Optimization
- Hallucination Reduction
- AI Evaluation
- Cloud Deployment
- Git
- Databases
- Rest APIs
- Vector Databases
- Embeddings
- Retrieval-Augmented Generation (RAG)
- Function Calling
- Machine Learning
- Model Deployment
- Computer Vision
- Neural Network Architecture
- Feature Engineering
- Backend Development
- LLM APIs
- Prompt Engineering
- Structured Outputs
- Context Management
- Python
Nice to Have Skills
- Independent Work
- Problem Solving
- Asynchronous Processing
- Multimodal AI
- AI Agents Development
- LlamaIndex
- LangGraph
- Langchain
- Production Monitoring
- CI/CD
- Docker