Description

Design and build Generative AI systems, including RAG and multi-agent applications, while maintaining core machine learning solutions.

This role is on-site.

Responsibilities

• Architect and deploy advanced RAG and GraphRAG applications using vector databases and knowledge graphs.
• Develop and maintain traditional ML models, including regression, classification, clustering, and time-series analysis.
• Build multi-agent systems using frameworks like LangGraph or AutoGen to automate complex analysis tasks.
• Implement evaluation frameworks (Ragas, DeepEval) to benchmark LLM performance and standard metrics.
• Write production-ready code in Python/TypeScript and manage CI/CD pipelines for scalable deployment via Docker and Kubernetes.

Required Skills

• 3-5 years of professional engineering experience with expert proficiency in Python.
• Proven experience applying traditional ML techniques (Random Forest, XGBoost, Linear/Logistic Regression).
• Deep hands-on experience with LLM orchestration tools (LangChain, LlamaIndex).
• Production experience with Vector Databases (Pinecone, Weaviate, Chroma) and Hybrid Search.
• Solid experience with cloud platforms (GCP, AWS, Azure), Docker, and Git.
• Experience with Prompt Engineering techniques (CoT, ReAct) and structured outputs.
• Familiarity with Transformers, Embeddings, Feature Engineering, and Model Evaluation fundamentals.

Preferred Skills

• Experience with Knowledge Graphs (Neo4j) or GraphRAG implementations.
• Proficiency in TypeScript for backend and frontend integration.

Key Skills

Education

Any Gradute