GenAI Engineer at Saransh Inc in Hartford, Connecticut

Job Description:

• The Generative AI team is comprised of a multiple cross-functional group that works in unison and ensures a sound move from our research activities to scalable solutions.
• You will collaborate closely with our cloud, security, infrastructure, enterprise architecture and data science team to conceive and execute essential functionalities.

• Design and build fault-tolerant infrastructure to support the Generative AI Ref architecture (RAG, Summarization, Agent etc).
• Ensure code is delivered without vulnerabilities by enforcing engineering practices, code scanning, etc.
• Build and maintain IAC (terraform/Cloud Formation), CICD (Jenkins) scripts, CodePipeline, uDeploy, & GitHub Actions.
• Partner with our shared service teams like Architecture, Cloud, Security, etc to design and implement platform solutions.
• Collaborate with the DS team to develop a self-service internal developer Generative AI platform.
• Design and build the Data ingestion pipeline for Finetuning LLM Models.
• Create templates (Architecture As Code) implementing Ref architecture application's topology.
• Build a feedback system using HITL for Supervised finetuning.

• Bachelor's degree in Computer Science, Computer Engineering, or a technical field.
• 4+ years of experience with AWS cloud.
• At least 8 years of experience designing and building data-intensive solutions using distributed computing.
• 8+ years building and shipping software and/or platform infrastructure solutions for enterprises.
• Experience with CI/CD pipelines, Automated Testing, Automated Deployments, Agile methodologies, Unit Testing and Integration Testing tools.
• Experience with building scalable serverless application (real-time / batch) on AWS stack (Lambda + step function)
• Knowledge of distributed NoSQL database systems.
• Experience with data engineering, ETL technology, and conversation UX is a plus.
• Experience with HPCs, vector embedding, and Hybrid/Semantic search technologies.
• Experience with AWS OpenSearch, Step/Lambda Functions, SageMaker, API Gateways, ECS/Docker is a plus.
• Proficiency in customization techniques across various stages of the RAG pipeline, including model fine-tuning, retrieval re-ranking, and hierarchical navigable small-world graph (HNSW) is a plus.
• Strong proficiency in embeddings, ANN/KNN, vector stores, database optimization, & performance tuning.
• Extensive programming experience with Python, Java.
• Experience with LLM orchestration frameworks like Langchain, LlamaIndex etc.
• Foundational understanding of Natural Language Processing, and Deep Learning.
• Experience with CI/CD pipelines, Automated Testing, Automated Deployments, Agile methodologies, Unit Testing, and Integration Testing tools.
• Excellent problem-solving skills and the ability to work in a collaborative team environment.