Publicis Sapient is looking for Python Developers to join our team of bright thinkers and enablers. You will use your problem-solving skills, craft, and creativity to design and develop infrastructure interfaces for complex business applications. You will build and orchestrate agentic, GenAI-powered workflows that transform how our clients operate – from data ingestion and enrichment to intelligent, LLM-driven automation. We are on a mission to transform the world, and you will be instrumental in shaping how we do it with your ideas, thoughts, and solutions.
Your Impact:
-
Build and orchestrate agentic workflows using LangChain and LangGraph to power scalable, production-ready GenAI solutions.
-
Develop reusable components for data ingestion, transformation, enrichment, and validation that accelerate delivery across projects.
-
Ensure reliability, scalability, and traceability across agent workflows to support dependable, enterprise-grade AI applications.
-
Implement performance monitoring with tools like LangSmith and apply tuning mechanisms to continuously improve agent accuracy and efficiency.
-
Deploy and maintain Python-based GenAI services in production, leveraging Bitbucket, Git, and CI/CD tools for reliable releases.
-
Architect secure API communication and access management, using JWT, OAuth, and RBAC, to safeguard sensitive client data.
-
Apply NLP, LLM, and retrieval techniques, including vector stores and embeddings, to build context-aware, intelligent solutions for clients.
Your Skills & Experience:
-
Strong Python fundamentals (OOP, data structures, error handling) with hands-on experience using Pandas, NumPy, PySpark, or Dask.
-
Hands-on experience with LangChain, LangGraph, and Semantic Kernel, building agent orchestration, memory, and tool-use workflows.
-
Proficiency in Python API frameworks (Flask/FastAPI), with experience using IDEs such as VSCode and PyCharm.
-
Working knowledge of SQL/NoSQL databases, time-series data, and data modeling and schema design.
-
Basic integration experience with TensorFlow or PyTorch, plus exposure to vector databases (e.g., FAISS, Chroma) and embedding-based retrieval.
-
Proficiency with AWS Cloud Services and production deployment practices, including Bitbucket, Git, and CI/CD tools.
-
Strong understanding of security & access management – JWT, OAuth, RBAC – and secure API communication.
