Generative AI Engineer

Job Title: AI Engineer

Experience: 25 Years

Location: Chennai, Tamil Nadu, India

Work Mode: Remote / Hybrid options available (India Only)

Employment Type: Full-time

About the Role

We are seeking an experienced AI Engineer to design and implement advanced AI solutions, focusing on Retrieval-Augmented Generation (RAG) pipelines and large language model (LLM) applications. The role involves close collaboration with clients, handling project discussions, attending governance meetings, and ensuring timely delivery of milestones. Flexible remote work options are available.

Key Responsibilities

Design, develop, and deploy RAG pipelines in production environments.

Implement vector search solutions using modern vector databases.

Optimize semantic and sparse search strategies, including hybrid retrieval approaches.

Build and orchestrate LLM-based applications using frameworks like LangChain or LlamaIndex.

Perform prompt engineering and systematic testing for optimal model performance.

Apply context engineering techniques (chunking, token management, context window optimization).

Develop agentic systems with tool integration, planning, and multi-step reasoning.

Build high-throughput inference pipelines leveraging async programming patterns.

Collaborate with clients to understand requirements and provide technical guidance.

Lead project discussions, attend governance meetings, and ensure adherence to timelines.

Work closely with cross-functional teams to integrate AI solutions into business workflows.

Must-Have Skills

Proven experience with RAG pipelines in production.

Hands-on expertise with vector databases (Pinecone, Weaviate, Qdrant, Milvus, pgvector, MongoDB Atlas Vector Search).

Strong understanding of semantic and keyword-based search.

Proficiency in Python and modern AI development practices.

Experience with LLM orchestration frameworks (LangChain, LlamaIndex).

Knowledge of embedding models and trade-offs.

Familiarity with async programming and scalable inference systems.

Good-to-Have Skills

Experience with graph databases (Neo4j, Amazon Neptune) and knowledge graph construction.

Familiarity with AWS AI/ML services (Bedrock, SageMaker, Textract, Comprehend).

Exposure to evaluation and observability frameworks (LangSmith, Weights & Biases).

Background in traditional NLP or information retrieval.

Experience with LLM fine-tuning and multi-modal models.

Why Join Us

Work on cutting-edge AI technologies.

Engage directly with clients and influence strategic decisions.

Collaborative and innovative work environment.

Flexible remote work options.

Opportunities for continuous learning and growth.

How to Apply:

Send your resume to [Confidential Information]