Data / AI Engineer

Must Have: Python, SQL, Spark, Databricks, Cloud (Azure), Jenkins/Airflow, FastAPI, Langgraph, Langchain, MCP, Java, Scala, OpenAI

Nice to have: UI experience with ReactJS, AKS, Docker

Develop and manage scalable data pipelines.

Integrate data from multiple sources, ensuring consistency and reliability.

Build and deploy ETL process flows.

Understand data quality, validation, and privacy procedures.

Create and maintain clear documentation for data flows, systems, and processes.

Strong knowledge of Microsoft OpenAI APIs.

Solid understanding of embedding models and similarity search.

Proficient in building RAG pipelines.

Experienced in designing, building, training, and validating AI workflows using Langgraph and Langchain.

Work collaboratively with data engineers to create data products for agentic workflows.

Utilize the MCP pattern to design, build, and implement solutions.

Optimize agent workflows for greater accuracy and performance.

Familiar with agentic monitoring.

Integrate agentic workflows with APIs and UIs.

Experience in software system development, including API creation, functional programming, design patterns, threads, and schedulers.

Skilled in building CI/CD process flows.

Strong knowledge of building Docker images and publishing to ACR (Azure Container Repository).

Document model architectures, parameters, and development processes.

Note: Job Description and Background Check

Candidates may be subjected to a Background Check /Drug Test as required by the end client before the assignment starts.