Key Responsibilities :
AI System Design & Development :
- Architect, develop, and deploy large-scale Generative AI, LLM-based systems, including intelligent agents and automation workflows.
LLM Integration & Optimization :
Integrate and optimize large language models for reasoning, summarization, and structured content generation.Apply prompt design, fine-tuning, and evaluation strategies to ensure reliable and domain-aware outputs.Knowledge & Retrieval Systems :
Design and implement retrieval-augmented and context-aware AI pipelines, combining embeddings, semantic search, and hybrid retrieval methods.Backend Engineering :
Build robust, scalable backend services and APIs using TypeScript and Python, including real-time communication and data streaming capabilities.Ensure high performance, fault tolerance, and clean integration between AI components and backend systems.Data Pipelines & Processing :
Develop and manage pipelines to extract, process, and transform unstructured data (code, documents, text) into AI-ready formats.Infrastructure & Deployment :
Design and maintain cloud-native, containerized, and event-driven architectures with Infrastructure-as-Code (IaC) practices.Collaborate with DevOps teams to implement CI / CD, observability, and environment automation.Model Evaluation & Monitoring :
Establish model evaluation metrics, continuous validation workflows, and performance dashboards to ensure production reliability and drift detection.Leadership & Mentorship :
Lead design discussions, perform technical reviews, and mentor AI engineers.Collaborate cross-functionally with product and platform teams to translate AI capabilities into production-grade solutions.Required Skills
Strong proficiency in Python and TypeScript , with a solid background in backend or API development.Proven experience in LLM-based application design , Generative AI workflows , or AI agent systems .Understanding of retrieval-augmented generation (RAG) and semantic / embedding-based search principles.Experience building scalable cloud-native services , including event-driven or asynchronous architectures.Familiarity with infrastructure automation , container orchestration , and CI / CD pipelines .Exposure to MLOps principles — model lifecycle management, evaluation, and continuous improvement.Strong problem-solving, analytical, and architectural reasoning skills.Excellent communication, collaboration, and mentoring abilities.Preferred Qualifications & Experiences :
Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or related disciplines .3+ years of professional experience in AI / ML software engineering , including 2+ years in Generative AI or LLM-based systems .Previous experience leading small engineering teams or driving architectural decisions is highly preferred.