AI Software Engineer
Job Summary
We are seeking an AI Software Engineer to architect and develop LLM-based solutions, including RAG systems and GenAI applications. You will work in a fast-paced environment to integrate AI capabilities with cloud platforms like Azure and AWS. The role focuses on building scalable, production-ready AI systems that drive innovation and enhance user experience.
Responsibilities
- Architect and deploy GenAI and RAG solutions
- Develop and maintain scalable AI systems
- Integrate cloud-based AI services (Azure/AWS)
- Build and optimize vector/graph databases
- Collaborate with product teams on AI features
Required Skills
- Python / Node.js / JavaScript
- LLM Frameworks (LangChain, LlamaIndex)
- Vector/Graph Databases (Pinecone, Neo4j)
- Cloud AI (Azure AI Foundry, AWS Bedrock)
- RAG Architecture & Prompt Engineering
Job Details
Key Responsibilities
- Architect, develop, and deploy AI solutions such as GenAI.
- Design and implement systems for knowledge-intensive AI applications such as Retrieval-Augmented Generation (RAG).
- Explore, evaluate, and adopt emerging AI frameworks, tools, and technologies to maintain competitive advantage.
- Build and optimize vector database and graph database solutions for semantic search and knowledge representation.
- Integrate AI capabilities with cloud platforms such as Azure AI Foundry and AWS Bedrock.
- Collaborate with product teams to identify opportunities for AI-driven feature enhancement.
- Develop and maintain scalable, production-ready AI systems with robust monitoring and evaluation.
- Document technical approaches, share knowledge, and contribute to the AI engineering culture.
Requirements
- Education: Degree or Diploma in Computer Science, Software Engineering or a related field.
- Experience: Minimum 3 years of software development experience with proficiency in Python and Node.js/JavaScript.
- 1+ years of hands-on experience building LLM-based AI applications.
- Demonstrable experience with RAG architectures, including document ingestion, chunking strategies, and retrieval optimization.
- Practical experience with vector databases (e.g., Pinecone, Weaviate, Milvus, or similar) or graph databases (e.g. Neo4j).
- Strong understanding of LLM application fundamentals and Agentic AI/Workflow architectures.
- Proficiency with LLM frameworks such as LangChain, LlamaIndex, or similar orchestration tools.
- Experience with cloud AI services, particularly Azure AI Foundry and AWS Bedrock.
- Understanding of API design, microservices architecture, and distributed systems.
- Knowledge of version control (Git) and CI/CD practices.
Key Competencies
- Fast Learner: Quickly grasp new concepts, frameworks, and technologies.
- Self-Learner: Proactively seek out new knowledge and experiment with emerging tools.
- Problem Solver: Analytical mindset to break down complex problems.
- Communication: Clear articulation of technical concepts to diverse stakeholders.
Nice to Have
- Experience with fine-tuning LLMs for domain-specific applications.
- Familiarity with LLMOps/MLOps practices and model deployment pipelines.
- Experience with prompt engineering and evaluation frameworks.