Description

You will design, build, and ship production-grade Generative and Agentic AI applications and services for internal and external users.

This role is on-site.

Responsibilities

• Develop high-quality backend services in Python with strong software engineering rigor around testing, performance, and maintainability.
• Build multi-agent systems using frameworks such as LangChain, LangGraph, Claude Agent SDK, and Google ADK.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking strategies, embeddings, vector search, and re-ranking.
• Implement clean, well-tested RESTful and/or gRPC APIs with a focus on reliability, security, and performance.
• Mentor and coach junior and mid-level engineers through code reviews, architecture discussions, and pair programming.

Required Skills

• 10-15 years of professional software engineering experience with at least 3-5 years of experience building AI/ML software products.
• Strong proficiency in Python, with deep software engineering fundamentals including abstraction, modularity, system design, testing, and performance.
• Hands-on experience building and shipping Generative and Agentic AI applications, including LLM integration, prompt engineering, and agentic workflows.
• Practical experience integrating cloud-hosted LLM APIs such as Azure OpenAI, Vertex AI, and/or AWS Bedrock.
• Experience with agent frameworks (e.g., LangChain, LangGraph, Google ADK, Claude Agent SDK) and vector databases (e.g., Pinecone, Weaviate, pgvector, Open Search, AlloyDB).
• Hands-on experience with Google Cloud Platform (GCP), Amazon Web Services (AWS), or Azure.
• Strong understanding of API design, distributed systems, and cloud-native architecture.

Preferred Skills

• Master's degree in Computer Science or a related field.
• Proven track record of taking systems from design through production deployment and operation.

Key Skills

Education

Bachelor's degree