LLM Engineer

BeaconFire Inc.; Connecticut; On-site; USD 110,000 - 170,000; Full time

Job summary

BeaconFire Inc. is seeking a skilled Python web developer to design and build high quality web applications using Flask and Django, focusing on maintainable code and scalable architectures.

You will design RAG pipelines on Google Cloud / Vertex AI, build agentic workflows, perform code reviews and testing, and contribute to documentation, planning and evaluation to improve system quality. The role emphasizes staying current with evolving technologies and delivering production APIs,

Qualifications

• Proficiency in Python web development and RESTful APIs.
• Experience with Flask or Django in production.
• Knowledge of RAG systems and embeddings.
• Familiarity with cloud services and Vertex AI.

Responsibilities

• Collaborate with the team to design and develop Web applications using Python, Flask, Django, and related technologies.
• Write clean, efficient code with maintainability in mind.
• Design and implement RAG pipelines on Google Cloud / Vertex AI (chunking, embeddings, indexing, retrieval, reranking, grounding).
• Build agentic workflows using Python-first frameworks (tool use, planning, reflection/guardrails, structured outputs).
• Perform code reviews to ensure quality and consistency.
• Conduct testing to ensure application reliability.
• Create and maintain technical documentation for web applications.
• Participate in project planning, estimation, and prioritization.
• Stay up to date with Python development technologies.
• Define and run evaluation (retrieval metrics, answer quality, grounding checks).
• Ship to production: APIs, monitoring/observability, cost/performance optimization, CI/CD, and security best practices.

Skills

Python

Flask

Django

RAG pipelines

Google Cloud Vertex AI

agentic workflows

CI/CD

security best practices

documentation

project planning

testing

code reviews

Tools

Git

LangGraph/LangChain

LlamaIndex

Semantic Kernel

AutoGen

Job description

• 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.

Requirement:

• Decent understanding of the software development/testing life cycle.
• Knowledge of relational databases (e.g. MySQL, PostgreSQL, etc)slanguage skills
• Experience with version control tools, such as Git.
• Experience building RAG solutions (hybrid search, reranking, chunking strategies, embeddings, prompt + schema design).
• Familiar with at least one agentic framework (e.g., LangGraph/LangChain, LlamaIndex, Semantic Kernel, AutoGen) and tool/function calling patterns.

Preferred Qualifications:

• 1+ year professional experience in Python web application development with either Flask or Django.
• Experience in RESTful API development in Python.
• Understanding of Python web application frameworks such as Flask or Django.
• 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).