Lead GenAI Engineer - Python/LLM

About the Organisation

Our client is an established organisation in the Education Technology and Learning Solutions sector, focused on making quality education and learning opportunities more accessible through technology.

With a strong presence in the education ecosystem, the organisation leverages digital platforms and technology-driven solutions to address evolving learning needs.

The organisation is expanding its AI capabilities and investing in next-generation Generative AI solutions. This opportunity offers the chance to contribute to enterprise-scale AI initiatives, develop intelligent applications and drive the adoption of Agentic AI and LLM-powered solutions.

Role Overview

We are looking for an experienced and hands-on Lead GenAI Engineer to drive the architecture, development and deployment of enterprise-grade Generative AI applications.

The ideal candidate should have strong expertise in Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI and Multi-Agent architectures.

This role requires an engineer who can take AI solutions beyond prototypes and proof-of-concepts and successfully transition them into scalable, reliable and production-ready systems.

You will be responsible for leading technical implementation, designing AI architectures, optimising model performance, establishing LLMOps/MLOps practices and mentoring engineering teams.

We are looking for someone who combines strong hands-on engineering capabilities with technical leadership and end-to-end solution ownership.

Key Responsibilities

1. GenAI Architecture & Engineering:

- Lead the GenAI roadmap, taking solutions from prototypes and proof-of-concepts to production.

- Design, develop and deploy enterprise-grade applications powered by Large Language Models.

- Architect and implement Retrieval-Augmented Generation (RAG) pipelines.

- Develop LLM-powered applications with contextual retrieval and intelligent response generation.

- Design scalable and secure GenAI architectures for enterprise use cases.

2. Agentic AI & Multi-Agent Systems:

- Design and develop Agentic AI and Multi-Agent systems.

- Work with frameworks such as LangGraph and Google Agent Development Kit (ADK).

- Implement agent orchestration, tool calling and enterprise system integrations.

- Explore and implement MCP (Model Context Protocol) and A2A (Agent-to-Agent) communication.

- Build intelligent workflows involving multiple specialised AI agents.

3. Edge AI & Model Optimisation:

- Drive Edge AI initiatives using technologies such as Ollama and vLLM.

- Implement model quantisation, distillation and inference optimisation techniques.

- Evaluate efficient model-serving strategies for different deployment environments.

- Optimise inference speed, resource utilisation and model performance.

4. LLMOps, MLOps & Production Deployment:

- Establish LLMOps/MLOps best practices across the GenAI development lifecycle.

- Implement CI/CD pipelines for AI application development and deployment.

- Establish observability, logging, monitoring, testing and AI guardrails.

- Ensure production AI applications meet reliability, scalability and security requirements.

- Continuously monitor and improve deployed models and applications.

5. Performance, Scalability & Reliability:

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

- Identify and resolve performance bottlenecks in LLM applications and retrieval pipelines.

- Design robust architectures capable of supporting enterprise workloads.

- Implement appropriate security controls and production AI best practices.

6. Technical Leadership:

- Provide technical direction and mentorship to engineering teams.

- Conduct architecture reviews, code reviews and technical assessments.

- Establish engineering standards and development best practices.

- Collaborate with stakeholders to translate business requirements into technical solutions.

- Take ownership of end-to-end GenAI engineering initiatives.

Required Technical Skills:

Programming & Development:

- Strong hands-on proficiency in Python.

- Experience developing APIs and production-grade applications.

Generative AI & LLMs:

- Large Language Models (LLMs).

- Retrieval-Augmented Generation (RAG).

- Agentic AI and Multi-Agent Systems.

- Embeddings and Vector Databases.

- LLM-powered application development.

Agentic AI Frameworks & Protocols:

- LangGraph.

- Google Agent Development Kit (ADK).

- Model Context Protocol (MCP).

- Agent-to-Agent (A2A) communication.

Edge AI & Model Serving:

- Ollama.

- vLLM.

- Model quantisation and distillation.

- Inference optimisation.

MLOps / LLMOps:

- CI/CD.

- Observability and monitoring.

- AI guardrails and testing.

- Production deployment and lifecycle management.

Cloud Platforms:

- AWS.

- Google Cloud Platform (GCP).

- Microsoft Azure.

Mandatory Experience & Qualifications:

- Minimum 8+ years of overall professional experience.

- At least 3+ years of hands-on experience building and deploying production GenAI/LLM systems.

- Strong practical experience in Python and LLM-based application development.

- Demonstrated experience implementing RAG pipelines and Agentic AI solutions.

- Hands-on experience with LangGraph and/or Google ADK.

- Understanding of embeddings, vector databases and retrieval architectures.

- Experience working with at least one major cloud platform: AWS, GCP or Azure.

- Practical understanding of LLMOps/MLOps, CI/CD and production AI systems.

- Ability to design technical architectures and provide engineering leadership.

- Strong analytical, problem-solving and communication skills.

What We Are Looking For:

- The ideal candidate should have personally designed, developed and deployed production-grade GenAI applications.

- Be able to explain the architecture, implementation decisions and challenges of systems they have built.

- Possess strong knowledge of RAG architecture, agent orchestration and LLM application development.

- Understand production challenges involving scalability, security, latency, reliability and cost optimisation.

- Be comfortable writing and reviewing code while leading technical initiatives.

- Have the ability to mentor engineers and drive engineering excellence.

Important: This is a hands-on engineering leadership position, not a purely managerial or product-management role. Candidates with only theoretical AI knowledge, general AI/ML exposure or limited POC experience may not be suitable.