Senior FastAPI Engineer - AI Backend & LLM Orchestration

Newcode.ai; New York (NY); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Flexible, English-speaking environment

Collaborative, high-energy team

Job summary

Newcode.ai is building AI tools for professional services. You will own the backend behind AI features, including APIs, data pipelines, and orchestration between our product and language models.

You’ll design retrieval over large document sets, ensure dependable LLM interactions, and stream results to the UI at production scale. The role emphasizes robust architecture decisions, fast, secure processing of confidential data, and ownership of long-running jobs.

Qualifications

• Requires 7+ years building production backend systems.
• Focus on reliability, scalability, and security for confidential data.
• Experience with LLM-powered systems, RAG, tool-calling, and agents is a plus.
• Proficient in Python and FastAPI development stack.
• Familiarity with distributed systems and async processing.

Responsibilities

• Design and build APIs and services powering products.
• Work on AI plumbing: retrieval, orchestration, tool-calling, streaming responses.
• Ensure reliability of async and distributed tasks: ingestion, embeddings, long jobs on Redis.
• Integrate with systems clients use (email, document stores) and ensure load handling.
• Prioritize data security and isolation in production.

Skills

Python

FastAPI

PostgreSQL/SQL

Redis

LangChain

LlamaIndex

Tools

LangChain

LlamaIndex

Job description

Newcode.ai is building AI tools for professional services. You will own the backend behind AI features, including APIs, data pipelines, and orchestration between our product and language models.

You’ll design retrieval over large document sets, ensure dependable LLM interactions, and stream results to the UI at production scale. The role emphasizes robust architecture decisions, fast, secure processing of confidential data, and ownership of long-running jobs.