Gen AI Engineer

Job Title : Gen AI Engineer

Experience: 5+ Years

Location: Onsite (Pune)

Duration : 3 to 6 Months

We are seeking a GenAI Engineer to design, build, and deploy Generative AI solutions that enhance business workflows and user experiences. The ideal candidate will have strong hands-on expertise in Large Language Models (LLMs), prompt engineering, and Retrieval-Augmented Generation (RAG), with the ability to integrate AI capabilities into scalable, production-grade applications.

Responsibilities:

Model Integration & APIs

• Integrate and fine-tune LLMs (OpenAI / Azure OpenAI / Open-source models)
• Build scalable APIs and microservices for GenAI-powered features
• Deploy GenAI solutions using Docker and Kubernetes

Prompt Engineering

• Design, optimize, and evaluate prompts for accuracy, safety, and performance
• Implement guardrails, prompt versioning, and evaluation strategies

RAG (Retrieval-Augmented Generation)

• Build end-to-end RAG pipelines:
• Document ingestion
• Chunking strategies
• Vector embeddings
• Semantic search
• Implement Top-K retrieval and re-ranking techniques

Application Development

• Integrate GenAI features into web/mobile applications
• Develop APIs using FastAPI / Flask / Django
• Build interactive GenAI apps using Streamlit or React

Real-Time AI & Streaming

• Implement streaming responses using Server-Sent Events (SSE) or WebSockets
• Optimize perceived latency for LLM-based applications

Optimization & Monitoring

• Monitor token usage, latency, and inference costs
• Implement cost-optimization strategies and performance tuning
• Track model quality and drift

AI Safety & Governance

• Implement moderation, bias detection, and responsible AI guidelines
• Ensure compliance with AI safety best practices

Required Skills

• Programming: Python (FastAPI, Flask, Django)
• LLMs & GenAI: OpenAI APIs, Azure OpenAI, Prompt Engineering
• RAG & Search: Vector embeddings, semantic search
• Vector Databases: Pinecone, Weaviate, FAISS
• Cloud Platforms: AWS / Azure / GCP
• DevOps: Docker, Kubernetes, Microservices
• ML Fundamentals: Embeddings, tokenization, similarity metrics
• Real-Time AI: SSE, WebSockets

Preferred / Good-to-Have Skills

• LangChain, LlamaIndex
• Image generation models (Stable Diffusion)
• MLOps, CI/CD pipelines
• Model evaluation techniques (LLM-as-a-Judge)
• Cost monitoring and inference optimization
• Experience with Matryoshka embeddings or vector compression techniques