Agentic AI Developer (Python)

BeaconFire Inc. • United States

Visa Sponsorship

This Job is No Longer Active This position is no longer accepting applications

AI Summary

BeaconFire is seeking an Agentic AI Developer to design, build, and productionize Vertex AI–based RAG systems and agentic workflows. The role involves end-to-end delivery including ingestion, retrieval, agent orchestration, evaluation, and deployment of web applications using Python and related frameworks. Candidates must have strong Python development experience, RAG solution building experience, and solid engineering practices.

Key Highlights

Build and productionize Vertex AI–based RAG systems (Vertex AI Search / Vertex AI RAG patterns)

Design reliable tool-using agents and agentic workflows using Python-first frameworks

Own end-to-end delivery: ingestion, retrieval, agent orchestration, evaluation, and deployment

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

Key Responsibilities

Collaborate with the team to design and develop high quality Web applications using Python, Flask, Django, and related technologies

Write clean and efficient code, and ensure code maintainability and reusability

Design and implement RAG pipelines on Google Cloud / Vertex AI (chunking, embeddings, indexing, retrieval, reranking, grounding)

Build agentic workflows (tool use, planning, reflection/guardrails, structured outputs) using Python-first frameworks

Perform code reviews to ensure code quality and consistency

Conduct testing to ensure application quality and reliability

Create and maintain technical documentation for web applications

Participate in project planning, estimation, and prioritization

Stay up to date with the latest technologies for Python development

Define and run evaluation (retrieval metrics, answer quality, hallucination/grounding checks), and improve system quality iteratively

Ship to production: APIs, monitoring/observability, cost/performance optimization, CI/CD, and security best practices

Technical Skills Required

Python RAG systems Vector databases

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

Benefits & Perks

Visa sponsorship provided

Equal employment opportunities

Interested in opportunities specifically in United State? Discover our dedicated Visa Sponsorship Jobs in United State page featuring roles from top employers in this location.

Nice to Have

Master’s Degree in Computer Science, Software Engineering, or related field

1+ year professional experience in Python web application development with either Flask or Django

Experience in RESTful API development in Python

Experience with Cloud services, such as AWS

Experience with Vertex AI and GCP fundamentals (IAM, logging/monitoring, Cloud Run/GKE, storage)

Knowledge graphs for RAG (entity linking, graph traversal + retrieval fusion)

Streaming/messaging (Pub/Sub, Kafka), document pipelines (Document AI), and multilingual retrieval

Experience with evaluation tooling (RAGAS, TruLens, custom eval harnesses), prompt/version management

Frontend integration (basic React/Next.js) or platform enablement (internal developer tooling)

Job Description

Agentic AI Developer (Python)

BeaconFire is based in Central NJ, specializing in Software Development, Web Development, and Business Intelligence; looking for a strong agentic AI developer who can build and productionize Vertex AI–based RAG systems (Vertex AI Search / Vertex AI RAG patterns), design reliable tool-using agents, and work comfortably with vector databases and graph databases. You’ll own end-to-end delivery: ingestion, retrieval, agent orchestration, evaluation, and deployment.

Job Responsibilities

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.