About the Role:

We are hiring a Lead GenAI Engineer for a leading organisation in the education and learning domain that is investing in the development and deployment of next-generation Artificial Intelligence solutions. This is a senior technical role for someone who has moved beyond experimentation and POCs and has practical experience building, deploying and optimising LLM-powered applications, RAG pipelines, Agentic AI and Multi-Agent systems.

Key Responsibilities:

- Lead and contribute to the GenAI roadmap, taking initiatives from experimentation and proof of concept through production deployment.

- Design, architect and develop production-grade Generative AI and LLM-powered applications.

- Design and implement scalable Retrieval-Augmented Generation (RAG) pipelines.

- Work across document processing, embeddings, retrieval, vector search, contextual generation and response optimisation.

- Design and develop Multi-Agent AI systems and intelligent workflows for complex business use cases.

- Work with modern Agentic AI frameworks such as LangGraph, Google ADK and other relevant frameworks.

- Evaluate LLMs and AI models based on accuracy, performance, latency, scalability and cost.

- Work with Edge AI and local inference technologies, including Ollama, vLLM, model quantization and distributed inference.

- Establish and implement LLMOps/MLOps best practices for AI application lifecycle management.

- Build and maintain CI/CD processes, testing frameworks, observability, monitoring and deployment practices for AI systems.

- Implement appropriate AI guardrails, evaluation mechanisms and responsible AI practices.

- Optimise AI systems for scalability, reliability, latency, performance and cost efficiency.

- Collaborate with product, engineering and business stakeholders to translate business requirements into practical AI solutions.

- Research emerging GenAI technologies, models and frameworks and evaluate their applicability to business requirements.

- Provide technical leadership, mentoring and architectural guidance to engineering teams.

- Contribute to technical standards, architecture decisions and best practices for production AI engineering.

- Troubleshoot and resolve issues related to AI application quality, model performance, latency, reliability and scalability.

Required Skills:

- 8+ years of overall experience in software engineering, AI/ML or related technology domains.

- 3+ years of hands-on experience with Production GenAI / LLM systems.

- Strong programming experience in Python.

- Strong hands-on experience with Generative AI and Large Language Models (LLMs).

- Practical experience designing and implementing RAG-based applications.

- Strong understanding of Agentic AI and Multi-Agent architectures.

- Hands-on experience with frameworks such as LangGraph, Google ADK or equivalent Agentic AI frameworks.

- Experience with embeddings, vector databases and semantic search.

- Experience integrating LLM APIs and models into production applications.

- Strong understanding of LLMOps / MLOps and production AI lifecycle management.

- Experience with APIs, CI/CD and cloud-native architectures.

- Experience working with one or more cloud platforms such as AWS, GCP or Azure.

- Experience deploying, monitoring and maintaining production AI systems.

- Strong understanding of system scalability, reliability, observability and performance optimisation.

Contact:

yuktirecruiters@gmail.com