Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Sapient (publicissapient)Posted 18 days ago

Publicis Sapient - Senior Python/Generative AI Engineer

Who we'd reach at Sapient (publicissapient)Found and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Talent partner

Hires for this team

Senior teammate

On the team, can refer you

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a senior role for a Python and generative AI engineer, based in Gurgaon or Bangalore on a hybrid basis. It suits engineers with five to ten years of experience who have built and maintained LLM systems in production, not just prototypes. The work covers retrieval pipelines, agent workflows and evaluation for production AI applications, where reliability, latency and cost matter. The posting is published by Sapient, part of Publicis Sapient.

What you’ll do

  • Build backend services in Python.
  • Develop and take to production LLM applications such as RAG systems, agents and assistants.
  • Design prompt strategies, system instructions and evaluation logic.
  • Integrate vector databases and data pipelines.
  • Deploy scalable AI workloads on cloud platforms.
  • Work with product and data teams to turn business problems into AI systems.
  • Add observability, testing and guardrails for AI behaviour.

What they’re looking for

  • Strong Python fundamentals, including APIs, async processing and performance optimisation.
  • Hands-on experience building LLM applications with OpenAI or open-source models.
  • Experience with RAG architectures and embeddings.
  • Familiarity with LangChain, LlamaIndex or similar orchestration tools.
  • Experience with vector databases such as Pinecone, Weaviate, Milvus or FAISS.
  • Cloud exposure on AWS, Azure or GCP, and containerised deployments.
  • Understanding of prompt engineering, evaluation and hallucination handling.
  • Experience debugging production issues related to latency, reliability and scale.
  • The ability to explain technical trade-offs clearly.

Nice to have

  • Fine-tuning or adapters such as LoRA or PEFT.
  • Knowledge graphs or semantic search.
  • Model monitoring and evaluation frameworks.
  • Work with streaming pipelines.
  • Frontend integration for AI applications.

What’s on offer

  • Hybrid working between Gurgaon and Bangalore.

Skills

Questions about this role

Where is this job based?

Gurgaon or Bangalore, on a hybrid working basis.

How much experience is needed?

Five to ten years of experience is preferred.

Which skills matter most?

Strong Python, production LLM application experience, RAG and embeddings, and vector database experience.