Description

You will engineer scalable generative AI solutions, from complex agentic systems to production LLM deployments.

This role is on-site.

Responsibilities

• Architect complex Agentic Systems, including multi-agent orchestration, planning, and memory management.
• Drive the Distillation Strategy to convert massive models into smaller, task-specific models for cost efficiency.
• Build end-to-end solutions for business functions lacking engineering bandwidth.
• Engineer complex RAG pipelines and manage the deployment of LLMs at scale in production.
• Define best practices for AI-Native Development across the organization.

Required Skills

• 6+ years of experience with deep expertise in Distributed Systems and NLP.
• Proven experience deploying LLMs at scale.
• Proficiency in Python, LangChain, LangGraph, PyTorch, and HuggingFace.
• Experience with Vector Databases.
• Familiarity with Distributed Systems principles.
• Knowledge of NLP and TypeScript.
• Experience leveraging AI tools (e.g., GitHub Copilot) for coding and debugging.

Preferred Skills

• Experience with LlamaIndex, Pinecone, or Milvus.
• Familiarity with CI/CD for AI or Microservices architecture.

Key Skills

Education

Any Graduate