Role: GenAI Engineer

Location: In-Person Interview in NYC

Fulltime Role with Capgemini

Role Overview.

We are seeking an experienced GenAI Developer to design, build, and deploy Generative AI solutions powered by LLMs (Large Language Models). The ideal candidate will have hands-on experience in prompt engineering, RAG pipelines, LLM fine-tuning, and scalable AI system design.

You will work on cutting-edge AI use cases such as chatbots, copilots, document intelligence, and intelligent automation, leveraging modern frameworks and cloud platforms.

Key Responsibilities

Design and implement Generative AI applications using LLMs (GPT, Llama, Claude, etc.)

Build and optimize RAG (Retrieval-Augmented Generation) pipelines
Develop prompt engineering strategies for high accuracy and performance
Integrate LLMs with enterprise systems, APIs, and data sources
Work with vector databases (Pinecone, FAISS, Weaviate, Chroma)
Fine-tune and evaluate models using LoRA / PEFT techniques
Build and manage AI pipelines for real-time and batch use cases
Ensure latency, cost optimization, and scalability
Implement AI safety, guardrails, and monitoring mechanism
Collaborate with data engineers, backend teams, and stakeholder

Required Skill

Core GenAI & LLM Expertise

Strong experience with
OpenAI / Azure OpenAI / Hugging Face / Anthropic API
Deep understanding of
LLMs, Transformers, Embedding
Prompt engineering & prompt tuning
Hands-on experience with
RAG architecture
Context management & token optimization

Frameworks & Tool

Experience with
LangChain / LlamaIndex / Semantic Kerne
lVector DBs
Pinecone, FAISS, Milvus, Weaviate
Knowledge of
Knowledge graphs (optional but good)
Programming & Backend
Strong programming in
Python (mandatory)
Experience with FastAPI / FlaskREST APIs and microservices architecture Data & Cloud

Experience with

Azure / AWS / GCP AI service.
Handling
Unstructured data (PDFs, documents, logs)