Job Title : GenAI Engineer

Location : Chennai (Onsite/Hybrid)

Experience : 2-4 Years

Employment Type : Full-Time

Job Summary :

Key Responsibilities :

- Design, develop, and deploy Generative AI solutions using Large Language Models (LLMs).

- Build AI-powered chatbots, virtual assistants, document intelligence solutions, and automation platforms.

- Develop Retrieval-Augmented Generation (RAG) pipelines using enterprise data.

- Implement prompt engineering techniques to improve model accuracy and response quality.

- Integrate OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, or open-source LLMs into enterprise applications.

- Build scalable AI APIs and microservices using Python.

- Work with vector databases for semantic search and knowledge retrieval.

- Develop document ingestion and embedding pipelines.

- Fine-tune and optimize LLMs wherever applicable.

- Implement AI guardrails, content filtering, and responsible AI practices.

- Collaborate with product owners and business teams to understand AI use cases.

- Optimize latency, scalability, and cost of GenAI applications.

- Participate in architecture discussions and technical design reviews.

- Write reusable, maintainable, and well-documented code.

- Stay updated with the latest advancements in AI, LLMs, and Generative AI technologies.

Mandatory Skills :

- 2-4 years of software development experience.

- Strong programming skills in Python.

- Hands-on experience with Generative AI and Large Language Models (LLMs).

- Experience with OpenAI APIs, Azure OpenAI, Claude, Gemini, or similar LLM platforms.

- Good understanding of Prompt Engineering.

- Experience in developing RAG (Retrieval-Augmented Generation) applications.

- Knowledge of LangChain, LlamaIndex, or similar AI orchestration frameworks.

- Experience with vector databases such as :

1. Pinecone

2. FAISS

3. ChromaDB

4. Milvus

5. Weaviate

- Strong understanding of embeddings and semantic search.

- Experience building REST APIs using FastAPI or Flask.

- Good understanding of AI model deployment.

- Familiarity with Git and Agile development methodologies.

Preferred Skills :

- Experience with Hugging Face Transformers.

- Knowledge of open-source LLMs such as :

1. Llama

2. Mistral

3. Falcon

4. Phi

5. Gemma

- Experience with cloud platforms :

1. Microsoft Azure

2. AWS

3. Google Cloud Platform

- Docker and Kubernetes knowledge.

- Experience with CI/CD pipelines.

- Familiarity with ML lifecycle and MLOps.

- Knowledge of OCR technologies and document processing.

- Experience with AI agents and multi-agent frameworks.

- Knowledge of Model Context Protocol (MCP).

- Experience with AutoGen, CrewAI, or LangGraph.

- Understanding of AI evaluation frameworks.

- Experience integrating AI with enterprise applications.

Technical Skills :

1. Programming Languages :

- Python

- SQL

- JavaScript (Preferred)

2. AI/ML Frameworks :

- LangChain

- LlamaIndex

- Hugging Face

- Transformers

- PyTorch (Preferred)

- TensorFlow (Preferred)

3. LLM Platforms :

- OpenAI GPT

- Azure OpenAI

- Anthropic Claude

- Google Gemini

- Cohere

4. Vector Databases :

- Pinecone

- ChromaDB

- FAISS