Description

You transform research prototypes and GenAI workflows into scalable, production-grade systems.

Responsibilities

• Design and deploy Retrieval-Augmented Generation (RAG) pipelines and manage vector databases.
• Orchestrate multi-agent systems using frameworks like LangChain, CrewAI, or LangGraph.
• Build reusable frameworks and deployment pipelines to accelerate AI model production.
• Ensure AI solutions are scalable, secure, and responsibly implemented.
• Apply DevOps and observability principles to production services.

Required Skills

• 10+ years of software engineering experience in APIs, cloud deployments, and system integration.
• 3-5 years in ML engineering, with 2+ years in agentic or multi-agent systems.
• Proven experience building and deploying RAG pipelines using embedding models and vector search.
• Hands-on experience with vector databases such as FAISS, Pinecone, Weaviate, or Milvus.
• Experience with agent orchestration frameworks (LangChain, CrewAI, LangGraph, AutoGen etc).
• Advanced Python skills.
• Proficiency with AWS services (S3, Lambda, ECS, SageMaker, etc.).
• Strong background in cloud-native software engineering and microservices architecture.
• Understanding of Responsible AI principles.

Key Skills

Education

Bachelor's or Master's degrees