AI Engineer

Novacis Digital, LLC.; Rockville (MD); Remote; USD 120,000 - 170,000; Full time

Benefits offered by this job

Competitive salary

Dental insurance

Health insurance

Paid time off

Vision insurance

Job summary

Novacis Digital is seeking a passionate AI Engineer to design and build AI-powered applications using LLMs, RAG, and agentic AI approaches. You will implement services with Python and modern ML frameworks, and connect LLM platforms like OpenAI, Llama, and Hugging Face.

Responsibilities include building RAG systems, LangChain workflows, REST APIs with FastAPI/Flask, and ongoing evaluation of model performance, cost, and reliability.

Qualifications

• Strong background in AI/ML fundamentals and software engineering.
• Experience with Python and modern AI frameworks.
• Hands-on projects with LLMs, RAG, or agentic AI concepts.

Responsibilities

• Develop AI-powered applications with Python and ML frameworks.
• Implement LLM-based solutions using OpenAI, Llama, or Hugging Face.
• Build RAG apps with embeddings, vector DBs, and grounding.
• Create agentic AI workflows using LangChain and orchestration patterns.
• Develop RESTful APIs with FastAPI or Flask and ensure testing.
• Optimize prompts, token usage, latency, and costs.

Skills

Python

AI/ML fundamentals

LangChain

RAG

API design

Git

Docker

FastAPI/Flask

debugging

communication

Education

Bachelor's or master's in CS/AI/ML

Tools

OpenAI

Llama

Hugging Face

Pinecone

FAISS

PgVector

Job description

Benefits:

• Competitive salary
• Dental insurance
• Health insurance
• Paid time off
• Vision insurance

About the Role

We are looking for a passionate and hands-on AI Engineer to design and develop AI-powered applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI, and modern machine learning frameworks. The ideal candidate has strong Python fundamentals, practical project experience, and the ability to turn emerging AI capabilities into reliable product prototypes and production-ready services.

Key Responsibilities

• Develop AI-powered applications and services using Python and modern AI/ML frameworks.
• Build and integrate LLM-based solutions using OpenAI, Llama, Hugging Face, or similar foundation models and platforms.
• Develop RAG applications using embeddings, vector databases, document chunking, retrieval, reranking, and grounding techniques.
• Build agentic AI workflows using LangChain, LangGraph, tool/function calling, memory, and orchestration patterns.
• Develop REST APIs and lightweight backend services using FastAPI, Flask, or similar frameworks.
• Support prompt engineering, model/application evaluation, hallucination analysis, debugging, and performance optimization.
• Optimize token usage, prompt efficiency, context-window management, caching, latency, and LLM API costs while maintaining application quality.
• Prepare and transform structured and unstructured data for AI experimentation and product use cases.
• Use Git, Docker, automated testing, and CI/CD practices to support repeatable AI engineering workflows.Collaborate with product, cloud, data, QA, and solution architecture teams throughout the development lifecycle.
• Maintain technical documentation and evaluate new AI models, frameworks, and approaches for enterprise use cases.

Required Skills

• 1-4 years of professional, internship, research, or advanced project experience in AI/ML, Generative AI, or software engineering.
• Strong programming skills in Python.
• Solid understanding of Artificial Intelligence, Machine Learning, and Deep Learning fundamentals.
• Good understanding of Generative AI, LLM architectures, prompt engineering, embeddings, and vectorization.
• Hands-on project experience with OpenAI, Llama, Hugging Face, or similar models and platforms.
• Experience or strong exposure to LangChain, LangGraph, RAG, vector databases, and Agentic AI concepts.
• Experience with token usage optimization, prompt efficiency, context-window management, caching, latency, and LLM API cost optimization.
• Familiarity with System One decision models.
• Basic experience building APIs with FastAPI, Flask, or similar Python frameworks.
• Working knowledge of Git, Docker, SQL, pandas/NumPy, and software engineering practices.
• Strong analytical, debugging, logical, and communication skills.

Mandatory Project Experience

Candidates should demonstrate at least 2-3 hands‑on AI/GenAI projects involving one or more of the following:

• LLM-based applications or AI assistants.
• RAG solutions and vector database implementations.
• Agentic AI workflows or tool‑using agents.
• Prompt engineering and structured AI evaluation.
• Machine learning models using scikit‑learn, PyTorch, or TensorFlow.
• FastAPI/Flask-based AI services.
• AI solutions solving a real‑world business or operational problem.

Preferred Skills

• Exposure to Azure AI, Azure Machine Learning, AWS Bedrock, SageMaker, or equivalent cloud AI services.
• Experience with Pinecone, ChromaDB, FAISS, Qdrant, Milvus, pgvector, or similar vector databases.
• Exposure to Computer Vision, NLP, intelligent document processing, conversational analytics, or enterprise analytics.
• Experience applying token optimization techniques to improve the efficiency and cost of LLM-based applications.
• Experience with System One design.
• Experience with AI explainability and approaches that help users understand model outputs and application behavior.
• Familiarity with Docker, CI/CD, Linux, cloud deployment, or MLOps practices.

Educational Qualification

• Bachelor's or master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Information Technology, Computer Engineering, or a related engineering discipline.
• Candidates with strong academic performance and hands‑on AI projects will be preferred.

What We're Looking For

• Strong passion for AI and emerging technologies with a builder mindset.
• Ability to learn quickly, experiment, and convert concepts into working software.
• Strong ownership, curiosity, and willingness to test and improve your own work.
• Ability to work effectively in a fast‑paced product engineering environment.

About Novacis Digital

Novacis Digital is an AI-focused technology company developing intelligent solutions for government and commercial organizations. Our work spans intelligent document processing, analytics and insights, case management, conversational AI, and AI agents that support complex business workflows. We bring together product engineering, cloud technology, and industry expertise to turn emerging AI capabilities into practical solutions. At Novacis Digital, you will collaborate with a growing team, contribute to real‑world AI applications, and help shape products that improve how organizations process information, make decisions, and deliver services.

Flexible work from home options available.