GenAI Python Engineer
Role details
Job location
Tech stack
Job description
Prompt Engineering, React.js, Kafka, Docker, Kubernetes, Terraform, Jenkins, GitHub Actions, Databases (PostgreSQL, MongoDB, Oracle, Snowflake, * Design and implement Generative AI models for text, image, or multimodal applications.
-
Design and develop scalable full-stack enterprise applications using Python, FastAPI, and React.js.
-
Build and optimize RESTful and asynchronous APIs for secure enterprise integrations and AI-driven applications.
-
Develop and implement AI agent frameworks using MCP, LangChain, and LangGraph for enterprise use cases.
-
Design and implement Retrieval-Augmented Generation (RAG) pipelines for intelligent search and contextual query processing.
-
Develop microservices and distributed systems for AI agent lifecycle management and real-time data processing.
-
Implement CI/CD pipelines and automate deployments using Jenkins, GitHub Actions, Docker, and cloud services.
-
Work with databases and data pipelines to process large-scale structured and unstructured datasets
Requirements
We are seeking a highly skilled Python Developer with experience in building scalable enterprise applications and AI-powered platforms. The candidate has hands-on experience in Generative AI, LLM-driven applications, and agentic AI solutions using frameworks like LangChain, LangGraph, MCP, and RAG pipelines. Strong experience in API development, microservices architecture, ETL pipelines, and cloud-native solutions across AWS and Google Cloud Platform environments., * 4+ years of experience in Python development, AI applications, and enterprise systems.
- Hands-on experience with Generative AI, LLMs, and RAG-based solutions using LangChain and vector databases.
- Experience building agentic AI workflows using LangGraph and MCP frameworks.
- Strong experience in API and microservices development using FastAPI, Django, and Flask.
- Experience in CI/CD automation and containerized deployments using Docker and Kubernetes.
- Experience working on cloud platforms such as AWS and Google Cloud Platform with cloud-native architectures.
- Strong knowledge of databases including PostgreSQL, MongoDB, Oracle, Snowflake, and Teradata.
- Experience with ETL pipelines, distributed data processing, and tools like PySpark, Pandas, and AWS Glue.
- Experience with Kafka event streams and real-time data pipelines.
- Strong proficiency in Agile SDLC, performance optimization, and scalable system design.
Top 3 responsibilities you would expect the Subcon to shoulder and execute
- Strong experience in developing AI-powered applications, RAG pipelines, and agentic AI frameworks using Python, LangChain, LangGraph, and MCP.
- Strong experience in building scalable APIs, microservices, and cloud-native deployments with CI/CD automation.
- Strong experience in data processing, ETL pipelines, and integrating enterprise systems with AI solutions.