Senior Full Stack AI Engineer

Job Description:

We are seeking a highly skilled and motivated AI Engineer with a strong focus on Generative AI and Natural Language Processing (NLP) to join our dynamic team.

The ideal candidate will be instrumental in designing developing and deploying AI use cases that involve searching summarizing and creating themes from database and extensive and document repositories.

This role requires a deep understanding of modern AI techniques particularly those related to Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). This role will be responsible for writing code pairing with other developers as appropriate decomposing acceptance criteria to understand team backlog deliverables complexities and risk while working as a strong contributor on an agile team.

From a technical standpoint the Software Engineer has full-stack coding and implementation responsibilities and adheres to best practice principles including modern cloud-based software development agile and scrum code quality and tool usage.

Responsibilities:

Apply depth of knowledge and expertise to all aspects of the software development lifecycle as well as partner continuously with stakeholders on a regular basis

Develop and engineer solutions within an Agile software delivery team working to collaboratively deliver sprint goals write code and participate in the broader technical community and team-level Agile and Scrum processes.

Contribute to the design documentation and development of world-class enterprise applications leveraging the latest technologies and software design patterns.

Leverage technical knowledge of concepts and procedures within own area and basic knowledge of other areas to resolve issues as necessary.

Design and Development: Lead the design and implementation of end-to-end AI/ML pipelines for document understanding summarization and theme extraction. This includes data preprocessing feature engineering model training evaluation and deployment.

Generative AI Application: Develop and optimize LLM-based solutions for text summarization content generation and knowledge extraction from structured/unstructured data.

RAG System Implementation: Build and maintain robust Retrieval-Augmented Generation (RAG) pipelines leveraging vector databases and advanced indexing strategies to ensure

accurate and contextually relevant information retrieval.

Model Tuning and Optimization: Apply advanced GenAI tuning techniques such as QLORA LORA and PEFT to fine-tune pre-trained LLMs for specific use cases optimizing for performance efficiency and accuracy.

Vector Search and Embeddings: Implement and optimize vector search capabilities and embedding pipelines to enhance the efficiency and relevance of document searches and information retrieval.

Prompt Engineering: Develop and refine prompts to maximize the performance and accuracy of language models.

Collaboration: Work closely with cross-functional teams including product managers AI model teams and other engineers to understand business requirements and translate them into scalable AI/ML solutions.

Requirements:

Extensive Experience: Minimum of 5 years of proven software development experience.

Modern Application Development:

In-depth knowledge of modern application architecture principles.

Clear understanding of Data Structures and Object Oriented Principles

Practical experience with Artificial Intelligence (AI) tools for enhancing development workflows.

Proficiency in Microservices frameworks Event-Driven Services and Cloud-Native Application

Development.

Multiple years of experience on Service Oriented and Microservices architectures including

REST and GraphQL implementations

Strong Python Engineering: Expert-level proficiency in Python and relevant libraries (e.g.

FastAPI Pydantic PyTorch HuggingFace Ecosystem).

Experience with LLM-based pipelines: Proven experience in building and deploying applications

using Large Language Models.

Knowledge of vector search and embeddings: Hands-on experience with vector databases and

developing embedding pipelines.

RAG Concepts: Strong understanding and practical experience with Retrieval-Augmented

Generation (RAG) frameworks (e.g. LangChain LlamaIndex).

GenAI Tuning: Experience with generative AI tuning techniques such as QLORA LORA and PEFT.

MCP Experience: Practical experience with Agentic Workflows and Model Context Protocol

(MCP) for enhancing development workflows

NLP Expertise: Strong hands-on experience with NLP techniques such as text classification

summarization and topic modeling.

Full Stack Proficiency: Demonstrated ability to design develop and maintain both front-end and back-

end components of robust web applications.

Personal - Individual Use

Front-End Development: Strong expertise in developing intuitive user interfaces using contemporary

JavaScript frameworks (e.g. React) HTML5 and CSS.

Back-End Development: Solid experience in developing server-side logic and APIs using languages

Python Java or similar.

Database Expertise: Comprehensive knowledge of SQL and PL/SQL with a deep understanding of

Relational Database Management Systems (RDBMS) particularly Oracle.

API Development: Proven capability in designing developing and implementing high-performance

RESTful APIs leveraging appropriate frameworks and technologies.

CI/CD and DevOps:

Proficiency with Continuous Integration/Continuous Deployment (CI/CD) pipelines and tools for

building (e.g. Maven Gradle) and deploying code (e.g. Docker Jenkins OpenShift).

Experience with AWS is considered a significant advantage.

Agile Methodologies: Practical experience working within Agile development methodologies and utilizing

project management tools such as JIRA.

Testing Automation: Ability to develop and automate comprehensive unit integration and end-to-end

tests to ensure code quality.

Version Control: Solid understanding and practical experience with code versioning tools including

GitHub Enterprise.

Education:

Bachelors or Masters degree in Computer Science Artificial Intelligence Machine Learning Data