Senior AI Engineer

We are looking for a Senior Generative AI Engineer with deep hands-on expertise in building, fine-tuning, and deploying LLM-based and Generative AI applications. The ideal candidate will have strong engineering fundamentals combined with practical experience in designing production-grade GenAI systems.

Responsibilities:

• Design, build, and deploy Generative AI applications using LLMs (OpenAI, Anthropic, open-source models like Llama, Mistral, etc. )
• Develop and optimise RAG (Retrieval-Augmented Generation) pipelines, including chunking strategies, embeddings, and retrieval optimisation.
• Build agentic AI workflows and multi-agent systems using frameworks like LangChain, LangGraph, LlamaIndex, CrewAI, or AutoGen.
• Fine-tune and customise LLMs/foundation models using techniques like LoRA, QLoRA, PEFT, and RLHF.
• Design and implement prompt engineering strategies and evaluation frameworks for LLM outputs.
• Work with vector databases (Pinecone, Weaviate, FAISS, Milvus, ChromaDB) for efficient semantic search and retrieval.
• Build scalable APIs and microservices to serve GenAI models in production.
• Implement MLOps/LLMOps practices: model versioning, monitoring, observability, and CI/CD for GenAI pipelines.
• Optimise model inference for latency, cost, and throughput (quantisation, caching, batching).
• Collaborate with product managers, data scientists, and engineering teams to translate business use cases into GenAI solutions.
• Ensure responsible AI practices: hallucination mitigation, bias detection, guardrails, and content safety.
• Stay current with the fast-evolving GenAI landscape and evaluate new tools, models, and techniques.

Requirements:

• 8-11 years of overall software/ML engineering experience, with 2-3+ years of hands-on Generative AI/LLM experience.
• Strong proficiency in Python and experience with ML/DL frameworks (PyTorch, TensorFlow, Hugging Face Transformers).
• Hands-on experience with LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex).
• Practical experience building RAG systems and working with vector databases and embedding models.
• Experience with LLM fine-tuning techniques (LoRA, QLoRA, PEFT) and prompt engineering.
• Strong understanding of transformer architectures and foundation model internals.
• Experience deploying models/APIs on cloud platforms (AWS/Azure/GCP) using services like SageMaker, Bedrock, Azure OpenAI, or Vertex AI.
• Familiarity with containerization and orchestration (Docker, Kubernetes).
• Experience with MLOps/LLMOps tools (MLflow, Weights and Biases, LangSmith, etc. )
• Solid understanding of API development (FastAPI/Flask) and microservices architecture.
• Strong problem-solving skills and ability to work in a fast-paced, evolving domain.

Good to Have:

• Experience with multimodal AI (vision-language models, speech, etc. )
• Exposure to agentic AI frameworks and autonomous agent design patterns.
• Knowledge of model evaluation frameworks (RAGAS, DeepEval, etc. )
• Contributions to open-source GenAI projects or published research/blogs.
• Experience with GPU optimisation and distributed training/inference.
• Bachelor's/Master's degree in Computer Science, Engineering, or a related field.