Gen AI Architect

Colombo - Sri Lanka

Monthly Salary: Not Disclosed

Posted on: 12 hours ago

Vacancies: 1 Vacancy

Job Summary

Design build and deploy API-driven scalable GenAI solutions using modern technology stacks.
Integrate and orchestrate Large Language Models (LLMs) such as OpenAI GPT PaLM 2 Claude Cohere Dolly or similar via APIs.
Implement agent-based AI systems using frameworks such as LangChain or equivalent.
Design and manage vector-based retrieval systems using Pinecone Chroma FAISS or similar technologies.
Apply advanced prompt engineering techniques to optimize model outputs for business use cases.
Rapidly experiment with and evaluate new LLM versions and emerging GenAI capabilities providing insights and recommendations.
Build and maintain data pipelines supporting AI solutions handling both structured and unstructured data.
Perform data ingestion transformation and storage across source and target systems.
Collaborate with product and GenAI leads to deliver features aligned with the product backlog.
Debug troubleshoot and resolve software performance or architectural issues.
Design cloud-native AI infrastructure leveraging AWS Azure or GCP services for: Storage Serverless compute Search and retrieval TranscriptionConversational AI systems
Ensure AI solutions meet scalability reliability and maintainability standards.

Requirements

10 years of implementation experience in: Data analytics platforms OR Senior software development roles using modern technology stacks.
Strong programming expertise in at least one of the following: Python PySpark Java
Proven experience building API-based architectures and scalable backend services.
Hands-on experience integrating at least one enterprise-grade LLM via APIs.
Strong understanding of prompt engineering principles and best practices.
Demonstrated experience with LLM orchestration and agent frameworks.
Solid background in data engineering fundamentals including ETL processes.
Experience building and maintaining data pipelines and AI infrastructure.
Strong analytical and problem-solving skills with the ability to prototype rapidly.

Cloud & Platform Expertise

Hands-on experience with cloud platforms:AWS Azure Google Cloud Platform (GCP)
Familiarity with cloud-native services for:Data storage Serverless workflows Search & retrieval Speech-to-text and transcription Chat and conversational interfaces
Extensive experience with data engineering and ETL tools (highly desirable).

Education

Bachelors or Masters degree in:Computer Science Statistics Mathematics Or a related quantitative discipline

Desirable

Proven experience with Agentic AI systems.
Strong experimentation mindset with emerging AI models and tooling.
Ability to bridge technical implementation with product and business needs.
Experience working in cross-functional agile teams.

Design build and deploy API-driven scalable GenAI solutions using modern technology stacks.Integrate and orchestrate Large Language Models (LLMs) such as OpenAI GPT PaLM 2 Claude Cohere Dolly or similar via APIs.Implement agent-based AI systems using frameworks such as LangChain or equivalent.Design...

Design build and deploy API-driven scalable GenAI solutions using modern technology stacks.
Integrate and orchestrate Large Language Models (LLMs) such as OpenAI GPT PaLM 2 Claude Cohere Dolly or similar via APIs.
Implement agent-based AI systems using frameworks such as LangChain or equivalent.
Design and manage vector-based retrieval systems using Pinecone Chroma FAISS or similar technologies.
Apply advanced prompt engineering techniques to optimize model outputs for business use cases.
Rapidly experiment with and evaluate new LLM versions and emerging GenAI capabilities providing insights and recommendations.
Build and maintain data pipelines supporting AI solutions handling both structured and unstructured data.
Perform data ingestion transformation and storage across source and target systems.
Collaborate with product and GenAI leads to deliver features aligned with the product backlog.
Debug troubleshoot and resolve software performance or architectural issues.
Design cloud-native AI infrastructure leveraging AWS Azure or GCP services for: Storage Serverless compute Search and retrieval TranscriptionConversational AI systems
Ensure AI solutions meet scalability reliability and maintainability standards.

Requirements

10 years of implementation experience in: Data analytics platforms OR Senior software development roles using modern technology stacks.
Strong programming expertise in at least one of the following: Python PySpark Java
Proven experience building API-based architectures and scalable backend services.
Hands-on experience integrating at least one enterprise-grade LLM via APIs.
Strong understanding of prompt engineering principles and best practices.
Demonstrated experience with LLM orchestration and agent frameworks.
Solid background in data engineering fundamentals including ETL processes.
Experience building and maintaining data pipelines and AI infrastructure.
Strong analytical and problem-solving skills with the ability to prototype rapidly.

Cloud & Platform Expertise

Hands-on experience with cloud platforms:AWS Azure Google Cloud Platform (GCP)
Familiarity with cloud-native services for:Data storage Serverless workflows Search & retrieval Speech-to-text and transcription Chat and conversational interfaces
Extensive experience with data engineering and ETL tools (highly desirable).

Education