Senior Gen AI Engineer 

Job Description 

Brightly Software is seeking an experienced candidate to join our Product team in the role of Gen AI engineer to drive best in class client-facing AI features by creating and delivering insights that advise client decisions tomorrow.  

As a Gen AI Engineer, you will play a critical role in building AI offerings for Brightly. You will partner with our various software Product teams to drive client facing insights to inform smarter decisions faster. This will include the following: 

Lead the evaluation and selection of foundation models and vector databases based on performance and business needs 

Design and implement applications powered by generative AI (e.g., LLMs, diffusion models), delivering contextual and actionable insights for clients. 

Establish best practices and documentation for prompt engineering, model fine-tuning, and evaluation to support cross-domain generative AI use cases. 

Build, test, and deploy generative AI applications using standard tools and frameworks for model inference, embeddings, vector stores, and orchestration pipelines. 

                                                                                                                                                                                             Key Responsibilities: 

Guide the design of multi-step RAG, agentic, or tool-augmented workflows 

Implement governance, safety layers, and responsible AI practices (e.g., guardrails, moderation, auditability) 

Mentor junior engineers and review GenAI design and implementation plans 

Drive experimentation, benchmarking, and continuous improvement of GenAI capabilities 

Collaborate with leadership to align GenAI initiatives with product and business strategy 

Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector stores like Pinecone, FAISS, or AWS Opensearch 

Perform exploratory data analysis (EDA), data cleaning, and feature engineering to prepare data for model building. 

Design, develop, train, and evaluate machine learning models (e.g., classification, regression, clustering, natural language processing) with strong exerience in predictive and stastical modelling. 

Implement and deploy machine learning models into production using AWS services, with a strong focus on Amazon SageMaker (e.g., SageMaker Studio, training jobs, inference endpoints, SageMaker Pipelines). 

Understanding and development of state management workflows using Langraph. 

Develop GenAI applications using Hugging Face Transformers, LangChain, and Llama related frameworks 

Engineer and evaluate prompts, including prompt chaining and output quality assessment 

Apply NLP and transformer model expertise to solve language tasks 

Deploy GenAI models to cloud platforms (preferably AWS) using Docker and Kubernetes 

Monitor and optimize model and pipeline performance for scalability and efficiency 

Communicate techn