Key Responsibilities :
- Design, develop, and deploy agentic AI systems capable of autonomous decision-making, reasoning, and executing multi-step tasks.
- Build and fine-tune LLM-powered applications using frameworks like LangChain, LlamaIndex, or Semantic Kernel.
- Integrate LLMs into real-world workflows via APIs and tools (e.g., OpenAI, Hugging Face, Anthropic, Mistral).
- Architect and implement scalable pipelines for model orchestration, retrieval-augmented generation (RAG), and memory / long-context strategies.
- Develop robust interfaces between LLM agents and external tools, APIs, and databases.
- Experiment with prompt engineering, few-shot learning, and model evaluation techniques to optimise agent behaviour.
- Collaborate with cross-functional teams to understand business use cases and deliver end-to-end solutions.
Required Skills & Experience :
3+ years of experience in AI / ML, with a strong track record of freelance or consulting work.Proven experience with LLMs, prompt engineering, and agentic frameworks.Proficient in Python and familiar with modern LLM toolchains (e.g., LangChain, OpenAI Function Calling, ReAct, AutoGPT, AgentOps).Experience building autonomous or semi-autonomous agents capable of reasoning and planning.Solid understanding of vector stores (e.g., Pinecone, FAISS, Weaviate) and RAG pipelines.Knowledge of cloud platforms (Azure, AWS, GCP) and containerization (Docker, Kubernetes).Ability to work independently, manage clients, and deliver on fast-paced timelines.Job Types : Full-time, Permanent, Contractual / Temporary