AI Engineer

AI Engineer

Job Description
We are a technology-driven company building advanced, production-grade artificial intelligence solutions for complex real-world business problems. Our focus is on designing modern AI architectures, particularly large language model (LLM)–based systems, and delivering end-to-end AI pipelines from research and experimentation to scalable production deployment.
As an AI Engineer, you will play a key role in designing, building, fine-tuning, and optimizing LLM-powered systems. You will work hands-on with Retrieval-Augmented Generation (RAG) architectures, real-world data, and production environments, collaborating closely with data, backend, and product teams to deliver reliable, scalable, and high-impact AI solutions.

 
Responsibilities

AI & LLM System Development

• Design, develop, and optimize AI and LLM-based systems for production use
• Work with both open-source and API-based LLMs to support real-world business use cases

RAG Architecture & Retrieval Pipelines

• Design and implement Retrieval-Augmented Generation (RAG) pipelines using embeddings, vector databases, and retrieval strategies
• Optimize retrieval quality, relevance, and latency in production environments

Model Fine-Tuning & Evaluation

• Fine-tune language models for domain-specific tasks using supervised and instruction-based approaches
• Design and run evaluation, benchmarking, and validation workflows to measure model quality and performance

End-to-End AI Architecture

• Design scalable, end-to-end AI architectures from data ingestion and preprocessing to inference and serving
• Ensure systems are maintainable, observable, and production-ready

Collaboration & Integration

• Collaborate closely with data, backend, and product teams to integrate AI systems into existing platforms
• Translate product requirements into robust AI solutions

Documentation & Engineering Quality

• Produce clear technical documentation for models, pipelines, and architectural decisions
• Deliver scalable, maintainable, and well-engineered AI solutions
  
  

Required Skills & Qualifications

Must Have

• Minimum of 2 years of professional experience in Artificial Intelligence or Machine Learning
• Strong understanding of Machine Learning and Deep Learning fundamentals
• Hands-on experience working with Large Language Models (LLMs) such as GPT, LLaMA, Mistral, or similar
• Proven experience designing and implementing RAG pipelines in real-world projects
• Practical experience with model fine-tuning, prompt engineering, and evaluation methodologies
• Strong proficiency in Python and relevant ML frameworks such as PyTorch or TensorFlow
• Experience with modern LLM tooling and frameworks such as LangChain, LlamaIndex, or similar
• Familiarity with vector databases (e.g., FAISS, Pinecone, Weaviate, or equivalents)
• Solid understanding of MLOps concepts and hands-on experience deploying models in production environments
• Strong ability to analyze, test, and validate model outputs in real-world scenarios

• Familiarity with Docker, Kubernetes, and CI/CD pipelines
• Experience with distributed systems and large-scale data processing
• Experience optimizing latency and cost in LLM-based systems
• Background in advanced NLP or generative AI projects
• Contributions to open-source projects or published research