AI/GenAI Engineer

Position

About the Role

We're building a high-performance chat application an AI/GenAI Engineer to lead the integration and optimization of Large Language Models (LLMs). You'll be responsible for connecting LLM APIs, implementing domain-specific fine-tuning strategies, prompt engineering, and ensuring optimal performance for production use.

You'll work closely with our React and Python developers to create a seamless, intelligent chat experience that serves thousands of concurrent users.

Required Skills & Experience

Must Have:

• Strong hands-on experience building chatbots / conversational AI systems / AI Agents with LLMs and Generative AI technologies, including OpenAI, Anthropic Claude, and other major LLM APIs.
• Experience in Python frameworks such as FastAPI, LangChain, and LlamaIndex for building scalable LLM-powered applications.
• Experience in prompt engineering, chain-of-thought prompting, ReAct, and agent-based architectures.
• Proven expertise in RAG (Retrieval-Augmented Generation) systems using vector databases such as Pinecone, Weaviate, Qdrant, and ChromaDB.
• Familiarity with transformer architecture, attention mechanisms, and embedding models for semantic search and context retrieval.
• Experienced in fine-tuning and parameter-efficient adaptation (LoRA, QLoRA, PEFT), model quantisation, and optimisation for cost-effective inference.
• Practical knowledge of open-source models (Llama, Mistral, Falcon) and deployment using vLLM or TGI (Text Generation Inference).
• Skilled in API integration, webhooks, streaming responses, and function calling/tool use with LLMs.
• Experience in model evaluation using BLEU, ROUGE, BERTScore, and similar metrics for performance benchmarking.
• Proficient in MLOps, including experiment tracking (Weights & Biases, MLflow) and deployment pipelines on AWS SageMaker, Google Vertex AI, or Azure ML.
• Exposure to multi-modal models (vision, audio) and integration into unified AI workflows.
• Strong problem-solving, debugging, and optimization skills, including token cost analysis and inference efficiency.
• Contributions to the AI/ML community, including open-source or research-oriented publications.

Tech Stack: