HamburgerMenu
hirist

Publicis Sapient - Senior Python/Generative AI Engineer

TLG INDIA PRIVATE LIMITED
Multiple Locations
5 - 10 Years

Posted on: 20/02/2026

showcase-imageshowcase-imageshowcase-image

Job Description

Senior Python + Generative AI Engineer

Location : Gurgaon / Bangalore (Hybrid)

Experience : 5 - 10 Years

What youll actually work on :

Were looking for engineers who have moved beyond AI demos and notebooks people who have built, deployed, and maintained real systems powered by LLMs.

Youll design and build production-grade AI applications where reliability, latency, cost, and evaluation matter as much as accuracy.

Typical problems you may solve :

- Designing retrieval pipelines for enterprise knowledge

- Reducing hallucinations and improving response grounding

- Building agent workflows and tool integrations

- Scaling LLM applications on cloud infrastructure

- Monitoring and evaluating model performance in production

- Optimizing token usage, latency, and cost trade-offs

Core Responsibilities :


- Build backend services using Python

- Develop and productionize LLM applications (RAG / Agents / Assistants)

- Design prompt strategies, system instructions, and evaluation logic

- Integrate vector databases and data pipelines

- Work with cloud platforms to deploy scalable AI workloads

- Collaborate with product and data teams to translate business problems into AI systems

- Implement observability, testing, and guardrails for AI behavior

Required Skills :


- Strong Python fundamentals (APIs, async processing, performance optimization)

- Hands-on experience building applications using LLMs (OpenAI / open-source models)

- Experience with RAG architectures and embeddings

- Familiarity with frameworks like LangChain / LlamaIndex / similar orchestration tools

- Experience with vector databases (Pinecone, Weaviate, Milvus, FAISS, etc.)

- Cloud exposure (AWS / Azure / GCP) and containerized deployments

- Understanding of prompt engineering, evaluation, and hallucination handling

- Experience debugging production issues (latency, reliability, scaling)

Good to Have :

- Fine-tuning / adapters (LoRA / PEFT)

- Knowledge graphs or semantic search

- Model monitoring & evaluation frameworks

- Working with streaming pipelines

- Frontend integration for AI applications

What we value :

- Engineers who think in systems, not scripts

- Curiosity about failure modes, not just success cases

- Ability to explain technical trade-offs clearly

- Ownership from prototype production improvement

Location & Experience : Gurgaon / Bangalore

5- 10 years experience preferred

How to apply :

If youve built GenAI systems that people actually use (not just demos), Id love to talk.

Share your profile or GitHub and a short note on something youve shipped.


info-icon

Did you find something suspicious?

Similar jobs that you might be interested in