Gen AI - Senior Data Engineer

Company Description

BLEND360 is an award-winning, new breed Data Science Solutions Company focused on powering exceptional results to our Fortune 500/1000 clients and other organizations. We are a hyper growth company - born at the intersection of advanced analytics, data and technology.

BLEND360 is focused on their world-class people that help clients optimize business performance through data, technology and analytics.

BLEND360 has more than 900+ employees with offices in NYC, MD, CO, CA, Uruguay, Netherlands, UK and India. Blend360 continues to be one of the fastest growing companies, making the Inc. 5000 every year they have been in business. BLEND360 is known for our exceptional people, our get-it-done mentality, and delivering high impact and sustainable results. If you love to solve difficult problems and deliver results; if you like to learn new things and apply innovative, state-of-the-art methodology, join us at Blend360 

Job Description

• Proficiency with Pydantic and data validation in FastAPI. 
• Experience with containerization technologies (e.g., Docker, Kubernetes). 
• Familiarity with CI/CD pipelines and tools. 
• Knowledge of API design and implementation. 
• Experience with monitoring and logging tools (e.g., Prometheus, Grafana, other). 
• Knowledge of security best practices in microservices architecture. 
• Familiarity with version control systems (e.g., Git) and collaborative development workflows. 

Qualifications

• Bachelor's or Master's degree in Computer Science, Data Science, or a related field
• 4+ years of proven experience in leading technical teams and building applications using microservice architecture. 
• Extensive experience with Python and FastAPI. 
• Strong understanding of microservices principles and components such as logging, monitoring, health checks, scalability, resilience, service discovery, API gateways, and error handling. 

Nice to Have : 

• Experience working with Retriever models, including implementation of chunking strategies. 
• Knowledge and use of vector databases. 
• Understanding of optimal approaches in querying LLM models via API. 
• Prompt engineering knowledge, with familiarity in different strategies. 
• Exposure to various prompt engineering techniques in different scenarios.