Python Developer

About Us: BeaconFire is based in Central NJ, specializing in Software Development, Web Development, and Business Intelligence; looking for candidates who are good communicators and self-motivated. You will play a key role in building, maintaining, and operating integrations, reporting pipelines, and data transformation systems. Python Developer (AI / LLM / RAG / Web Development) Role Overview We are seeking a Python Developer with strong experience in AI/LLMs, Retrieval-Augmented Generation (RAG), and web development . You will build intelligent, scalable applications powered by large language models, integrating them into real-world products through robust backend systems and APIs. Key Responsibilities Design and develop backend systems using Python (FastAPI / Django / Flask) Build and integrate LLM-powered applications (chatbots, copilots, automation tools) Implement RAG pipelines for context-aware AI systems Work with vector databases (FAISS, Pinecone, Weaviate, Chroma) Develop and maintain RESTful / GraphQL APIs Handle data ingestion, chunking, embeddings, and retrieval workflows Integrate external APIs, third-party services, and AI models Optimize model responses, latency, and cost efficiency Collaborate with frontend, product, and DevOps teams Ensure code quality, testing, and deployment readiness Required Skills Strong proficiency in Python Experience with FastAPI / Flask / Django Solid understanding of LLMs (OpenAI, open-source models, etc.) Hands-on experience with RAG (Retrieval-Augmented Generation) Familiarity with embeddings, vector search, and semantic retrieval Experience with REST APIs and backend architecture Knowledge of databases (PostgreSQL, MongoDB) Basic understanding of prompt engineering Familiarity with Git and version control Preferred Skills (Good to Have) Experience with frameworks like LangChain / LlamaIndex Knowledge of transformers and Hugging Face ecosystem Experience with Docker, Kubernetes Familiarity with cloud platforms (AWS, GCP, Azure) Knowledge of streaming, async processing, WebSockets Experience with frontend (React / Next.js) for full-stack capability Understanding of model fine-tuning or LoRA RAG-Specific Expectations Build pipelines for: Document ingestion (PDFs, APIs, DBs) Text chunking and preprocessing Embedding generation Vector storage and retrieval Implement hybrid search (semantic + keyword) Optimize retrieval quality and reduce hallucinations Evaluate LLM outputs and improve accuracy Qualifications Bachelor’s degree in Computer Science, AI, or related field 0-2 years of experience in Python/backend development Hands-on experience with AI/LLM projects (internships or production)