Senior Data/AI Engineer

Role Overview

• Design and implement AI‑powered workflows such as agents, assistants, and tool‑enabled services.
• Build and maintain backend services using modern web frameworks and server‑side languages.
• Implement RAG‑style retrieval systems and contribute to prompt engineering and model interaction patterns.
• Integrate LLMs into production environments and develop scalable service layers around model inference and orchestration.
• Work with vector search technologies and embedding pipelines where needed.
• Design and operate ETL/ELT pipelines for batch, streaming, or hybrid workloads.
• Model data for analytics and application needs using best practices in schema design and storage optimization.
• Implement data quality, validation, auditing, and observability mechanisms.
• Ensure secure, reliable connectivity across cloud, on‑premise, and hybrid environments.
• Collaborate to define semantic business logic, reusable metrics, and shared data assets.
• Design and implement scalable APIs (REST, Queues, Events).
• Build integrations that connect AI systems to external applications, services, or platforms.
• Implement secure patterns for authentication, authorization, and secrets management.
• Ensure the overall backend architecture remains modular, maintainable, and extensible.
• Write and optimize complex queries across relational and NoSQL databases.
• Design efficient schemas, indexing strategies, and caching solutions to support high‑performance AI/data workloads.
• Conduct load/performance testing and implement safeguards to meet system reliability targets.
• Conduct and lead data Governance and data security best practices.
• Architect and implement systems for scalability, reliability, and security across backend and data layers.
• Add and maintain observability (logs, metrics, traces), alerting, and runbooks.
• Contribute to CI/CD, automation, and environment‑based deployments.
• Comply with privacy and security norms and rules such as PII, HIPAA, SOC 2 Type 2, or similar.
• Work with AI researchers to produce models and evaluate performance.
• Collaborate with the Solution Architect to align designs with long‑term architecture.
• Partner with Product to translate AI and data capabilities into meaningful user features.
• Stay informed on emerging AI, backend, and data engineering technologies and share knowledge with the team.

Requirements

• 7+ years of experience in data engineering with exposure to back-end engineering and AI‑powered systems.
• Proven experience delivering production‑grade services , APIs, and data pipelines end‑to‑end.
• Strong knowledge in one programming language for implementing data pipelines (Python, R, Java, Go, C#).
• Hands‑on experience integrating or building systems powered by large language models (LLMs) or similar AI technologies.
• Experience implementing RAG pipelines , vector search, or agentic automation frameworks (any stack).
• Knowledge on any AI Agent Framework (CrewAI, OpenAI, Langchain).
• Strong knowledge on Jupyter Notebook.
• Strong understanding of API design, service architecture, and secure integration patterns.
• Solid SQL skills and strong grounding in data modeling, schema optimization, and performance tuning.
• Familiarity with CI/CD pipelines, infrastructure automation, and cloud environments (any provider).

Tech Stack

• Cloud
• ETL
• Java
• NoSQL
• Python
• SQL
• Go

Benefits

• 20+ Paid time off days