Description

Lead the design, evaluation, and deployment of enterprise-grade Generative AI systems and autonomous Agentic AI workflows.

This role is remote.

Responsibilities

• Design scalable architectures for Agentic workflows (ReAct, Planning, Tool-Use) and multi-agent coordination frameworks.
• Build enterprise RAG systems with advanced retrieval methods including hybrid search, re-ranking, and graph RAG.
• Evaluate, benchmark, and fine-tune foundation models using LoRA/QLoRA and prompt optimization.
• Implement guardrails, evaluation pipelines (RAGAS, TruLens), and observability tools (LangSmith, Phoenix).
• Partner with product and DevOps teams to transition AI prototypes into secure, low-latency microservices.

Required Skills

• 8+ years in software design and machine learning, with 2+ years focused on Generative AI.
• Hands-on experience with LangChain, LangGraph, LlamaIndex, AutoGen, or CrewAI.
• Proficiency with vector search engines (Pinecone, Qdrant, Milvus, Weaviate, Pgvector).
• Expertise in Python and asynchronous APIs (FastAPI).
• Experience with cloud services (AWS Bedrock, Azure OpenAI, GCP Vertex AI).
• Containerization skills using Docker and Kubernetes.
• Demonstrated experience in LLMOps, tracking model latency, token costs, and drift.

Preferred Skills

• Experience with AI safety standards and cost-optimization strategies.
• Background in building custom tool-calling agents.

Key Skills

Education

Any Graduate