Gen AI Architect
Posted Updated
Summary
A GenAI Architect in Colombo who designs scalable, API-based generative AI solutions: integrating and orchestrating LLMs (OpenAI, Claude, PaLM, Cohere), applying prompt engineering and agentic frameworks like LangChain, using vector databases (Pinecone, Chroma, FAISS) and building data pipelines on Azure, AWS, or GCP.
- Design and develop scalable, API-based GenAI solutions integrated into business applications.
- Build and maintain data pipelines and infrastructure to support AI and LLM-based solutions.
- Integrate and orchestrate LLMs (e.g., OpenAI GPT, PaLM, Claude, Cohere) using API endpoints.
- Apply prompt engineering techniques and develop intelligent agent-based systems using frameworks such as LangChain.
- Work with vector databases such as Pinecone, Chroma, or FAISS for efficient information retrieval.
- Conduct experiments to evaluate and adopt new LLM models, features, and capabilities.
- Collaborate with GenAI Leads and cross-functional teams to address product backlog requirements.
- Troubleshoot and resolve system, integration, and design-related issues.
- Utilize cloud platforms (Azure, AWS, GCP) for storage, serverless computing, search, transcription, and conversational AI solutions.
- Contribute to architectural decisions and ensure best practices in AI system design and implementation.
Requirements
- Bachelor's or Master's Degree in Computer Science, Statistics, Mathematics, or a related field.
- Strong experience in data analytics, software development, or a senior engineering role within modern technology stacks.
- Proficiency in programming languages such as Python, PySpark, or Java.
- Experience building scalable API-driven architectures.
- Hands-on experience integrating at least one major LLM via APIs.
- Strong understanding of prompt engineering and LLM-based solution design.
- Experience with agentic AI frameworks and implementations.
- Knowledge of vector databases such as Pinecone, Chroma, or FAISS.
- Basic data engineering skills for handling structured and unstructured data.
- Experience with cloud platforms (Azure, AWS, or GCP).
- Familiarity with data engineering and ETL tools is an added advantage.
Core Competencies
- Strong analytical thinking and problem-solving skills.
- Ability to experiment, innovate, and adapt to rapidly evolving AI technologies.
- Strong collaboration and communication skills.
- Ability to design scalable and future-ready AI architectures.