Data Scientist

We are seeking a Data Scientist with deep technical expertise in large language models, autonomous agent design, and intelligent system orchestration. This role focuses on building self-directed, context-aware AI systems that can reason, learn, and interact with humans and software environments.

Key Responsibilities

• Design and build Agentic AI architectures capable of autonomous task execution, reasoning, and planning.
• Develop and optimize LLM-driven multi-agent systems that coordinate, collaborate, and adapt dynamically.
• Implement retrieval-augmented generation (RAG) and memory-based reasoning pipelines for intelligent context use.
• Conduct prompt engineering, few-shot learning, and reinforcement learning to fine-tune agent behavior.
• Build and manage knowledge graphs, embedding databases, and semantic retrieval layers to power reasoning.
• Architect data ingestion, context extraction, and interaction layers that enable AI agents to interface with real-world APIs, databases, and systems.
• Lead experimentation, evaluation, and optimization cycles to improve agent accuracy, autonomy, and decision quality.
• Collaborate with AI engineers and product teams to integrate agents into scalable production systems.

Technical Skills

• Core AI & ML: Python, PyTorch, TensorFlow, JAX, transformers, LLM tuning, prompt optimization
• Agentic Frameworks: LangChain, LlamaIndex, CrewAI, multi-agent orchestration
• Data & Knowledge Systems: FAISS, Pinecone, Milvus, Neo4j, ArangoDB
• Infrastructure: Docker, Kubernetes, AWS, GCP, Azure
• Advanced Capabilities: Self-improving agents, meta-learning, AI alignment, explainability

What You Will Work On

• Designing autonomous reasoning systems with dynamic objectives
• Building scalable AI agent platforms combining perception, reasoning, and execution