Experience:

• 6-10 Years

Role Focus:

• Design and implement end-to-end Generative AI systems using LLMs and RAG architectures
• Build scalable retrieval and vector search pipelines
• Develop custom agents, chains, and workflows
• Integrate OpenAI, Anthropic, Llama, or Mistral models
• Optimise prompt engineering, context retrieval, and embedding strategies
• Collaborate with backend teams to deploy AI microservices
• Implement MLOps practices for monitoring, versioning, and continuous delivery of AI models

Nice to have:

• Experience with LLMOps tools (e.g., Weights and Biases, MLflow, LangFuse, PromptLayer)
• Exposure to open-source LLMs (Llama 3, Mistral, Falcon, etc.) and custom fine-tuning
• Knowledge of knowledge graph integration or context-aware retrieval
• Familiarity with frontend integration using Streamlit, Gradio, or similar frameworks
• Contributions to open-source AI projects, research papers, or public demos

More skills:

Algorithms, Data Structures, Golang, Java, JavaScript, Scala, Anthropic, Llama, Mistral

Other:

• Strong programming skills in Python
• Hands-on experience with LangChain, LlamaIndex, or OpenAI / Hugging Face ecosystems
• Experience building RAG pipelines and integrating vector databases
• Deep understanding of LLM architectures, tokenisation, and prompt optimisation
• Experience with PyTorch or TensorFlow for model training or fine-tuning
• Familiarity with Docker, Kubernetes, and cloud deployment (AWS / GCP / Azure)
• Strong grasp of data engineering workflows, API integration, and system design