Description

You will develop and deploy production-grade AI services leveraging Python.

This role is on-site.

Responsibilities

• Develop Python back-end services integrating LLMs for reasoning, extraction, summarization, and decision support.
• Architect and implement autonomous/multi-agent workflows, including planning, tool-use, and memory management.
• Implement Retrieval Augmented Generation (RAG) pipelines, managing ingestion, chunking, embedding, and vector search.
• Define evaluation metrics and build suites to test AI quality, safety, and factual accuracy.
• Package, containerize, and deploy services using Docker and Kubernetes, managing CI/CD and cost governance.

Required Skills

• 15+ years of professional experience.
• Expert proficiency in Python, including typing, async programming, and testing.
• Experience building production APIs using FastAPI or Flask.
• Hands-on experience with LLMs (e.g., OpenAI, Azure OpenAI, Anthropic).
• Proven experience in prompt engineering, including few-shot strategies and tool/function calling.
• Experience with agent frameworks or custom orchestration (e.g., LangGraph, LangChain).
• Familiarity with vector databases (e.g., FAISS, Chroma, Pinecone).
• Practical understanding of ML/DevOps practices: Docker, CI/CD, and monitoring (Prometheus/Grafana).
• Knowledge of AI safety principles, including prompt injection defenses and data leakage prevention.

Key Skills

Education

Any Gradute