- Strong Python programming with hands-on AI/ML framework experience.
- Working knowledge of LLMs, prompt engineering, and basic fine-tuning (LoRA/QLoRA).
- Practical experience with agentic frameworks such as LangChain, AutoGen, or CrewAI.
- Experience with API integration and tool-augmented agent development.
- Understanding of responsible AI, safety guardrails, and LLM evaluation strategies.
- Familiarity with vector stores, retrieval systems, and RAG architectures
- Design and implement production-grade agentic architectures leveraging LLMs and reasoning engines.
- Build and optimise multi-agent systems for complex task orchestration and collaboration.
- Integrate external tools, APIs, and knowledge bases for robust agent augmentation.
- Tune agent performance for autonomy, adaptability, reliability, and safety.
- Embed agentic AI into enterprise workflows in collaboration with product teams.
- Prototype advanced capabilities: persistent memory, goal planning, and self-correction loops.
- Contribute to code reviews, technical documentation, and team best practices.
Good to Have
- Exposure to MLOps practices — experiment tracking, model versioning (MLflow, DVC).
- Knowledge of distributed systems and scalable backend architectures.
- Experience with cloud AI services on Azure, AWS, or GCP.