About the Role

We are looking for a motivated AI Engineer who is passionate about large language models (LLMs), machine learning, and applied AI systems. This position is focused on building real-world AI systems, not just experimenting with models.

You will work on projects involving open-source LLMs, retrieval-augmented generation (RAG) pipelines, vector databases, and AI-powered document processing systems. The goal is to build scalable AI workflows that solve practical problems such as knowledge retrieval, document analysis, and AI-assisted automation.

This role is ideal for engineers who want hands-on experience deploying AI systems used in production-like environments.

Responsibilities

AI & Machine Learning Development

• Build and experiment with open-source LLM and SLM pipelines.
• Design and implement Retrieval Augmented Generation (RAG) systems.
• Develop AI pipelines capable of processing documents, PDFs, and structured data.
• Work with embedding models and vector search systems.
• Implement prompt engineering, model evaluation, and response optimization.
• Assist with fine-tuning or adapting open-source models when necessary.

Data Processing & AI Pipelines

• Build ingestion pipelines for PDFs, documents, and datasets.
• Implement document chunking, embedding generation, and indexing strategies.
• Work with vector databases to support semantic search and retrieval.
• Optimize pipelines for latency, scalability, and cost efficiency.

Research & Experimentation

• Evaluate different open-source models and architectures.
• Compare embedding models and retrieval methods.
• Test improvements in RAG performance and hallucination reduction.
• Explore emerging techniques in Vision Language Models (VLMs).

Collaboration

• Work with engineers to integrate AI components into applications.
• Document experiments and technical findings.
• Participate in weekly discussions on AI architecture decisions and improvements.

Required Skills & Knowledge

Core AI Knowledge

• Strong understanding of:
• Machine Learning
• Neural Networks
• Deep Learning fundamentals
• Familiarity with:
• Large Language Models (LLMs)
• Small Language Models (SLMs)

Programming

• Strong proficiency in Python
• Experience with AI/ML frameworks such as:
• PyTorch
• TensorFlow
• Hugging Face Transformers

AI Application Frameworks

Experience with:

• LangChain or similar orchestration frameworks
• Prompt engineering and AI workflow building

Vector Databases

Conceptual and practical understanding of any vector databases such as:

• Pinecone
• ChromaDB
• Milvus
• Qdrant
• FAISS
• Weaviate

Understanding of:

• embeddings
• similarity search
• indexing strategies
• metadata filtering

RAG Systems

Ability to design or understand:

• Retrieval pipelines
• Document chunking strategies
• Embedding pipelines
• Hybrid search
• Context window optimization
• RAG evaluation methods

Data Processing

Experience with:

• PDF extraction
• Document parsing pipelines
• Data preprocessing

Bonus Knowledge

• Vision Language Models (VLMs)
• Multimodal AI systems
• Distributed AI inference
• GPU inference optimization

Preferred Project Experience

Candidates should have completed at least 1–3 hands-on AI projects, such as:

Example Project 1 – RAG Knowledge Assistant

• Built a chatbot that answers questions from internal documentation.
• Implemented document ingestion, chunking, embedding generation, and vector search.
• Used LangChain + vector database + open-source LLM.

Example Project 2 – Document AI System

• Created a system that extracts structured information from PDFs.
• Built pipelines for PDF parsing → embeddings → AI summarization.

Example Project 3 – AI Research Experiment

• Compared multiple embedding models and evaluated search accuracy.
• Benchmarked RAG response quality and hallucination rates.

Example Project 4 – LLM Application

• Built a real-world tool using open-source models (e.g., summarizer, Q&A system, coding assistant).

Real-World Experience

Candidates may also have experience such as:

• Contributing to open-source AI projects
• Participating in AI hackathons
• Research experience in machine learning or NLP
• Building production-style AI APIs
• Deploying models using Docker or cloud platforms
• Working with LLM inference servers (vLLM, TGI, Ollama, etc.)

Tools & Technologies (Exposure Preferred)

AI / ML

• PyTorch
• Hugging Face
• Transformers
• Sentence Transformers

LLM Tools

• LangChain
• LlamaIndex
• Open-source LLMs (LLaMA, Mistral, etc.)

Vector Databases

• Pinecone
• ChromaDB
• Milvus
• Qdrant
• FAISS
• Weaviate

Data Tools

• Pandas
• NumPy

Deployment

• Docker
• REST APIs / FastAPI
• Basic cloud exposure (AWS/GCP/Azure)

What You Will Gain

• Hands-on experience building real AI systems
• Exposure to modern LLM architecture and AI infrastructure
• Experience with RAG pipelines and vector databases
• Mentorship from engineers working in applied AI
• Opportunity to contribute to real production-style AI tools

Candidate Profile

We are looking for someone who:

• Is curious and loves experimenting with AI systems
• Enjoys solving practical engineering problems
• Can quickly learn new frameworks and models
• Is comfortable reading research papers and technical documentation
• Has strong problem-solving and debugging skills

Application Requirements

Please include:

• Resume
• GitHub profile (required)
• Links to AI/ML projects
• Brief description of a RAG or LLM system you have built

Pay: $60,000.00 - $80,000.00 per year

Work Location: In person