GenAI - Agentic WOrkflow - Engineer

About the Role  We are seeking a talented Generative AI Engineer to join our innovative team focused on building cutting-edge LLM-based knowledge retrieval and adaptive AI this role you will design optimize and deploy Retrieval-Augmented Generation (RAG) frameworks to enhance contextual intelligence semantic search and grounded AI outputs.

Youll collaborate with cross-functional teams to create scalable solutions that minimize hallucinations ensure data accuracy and drive real-world applications in domains like ADAS. If you thrive in a fast-paced environment and have a passion for prompt engineering and data-driven AI workflows this is your opportunity to shape the future of generative AI. 

Key Responsibilities  Design and implement prompting pipelines for semantic extraction and intelligent search incorporating fine-tuning techniques and evaluation metrics to optimize performance. 

Build adaptive knowledge retrieval pipelines using RAG frameworks vector databases for embedding and indexing and context management strategies. 

Optimize workflows for data alignment model validation and curation to deliver accurate grounded AI outputs that align with business needs. 

Conduct A/B testing for prompt efficiency and validate models against curated datasets to measure and improve system reliability. 

Develop strategies for chunking indexing and hybrid search using embedding models (e.g. OpenAI Cohere) to enhance retrieval accuracy and speed. 

Collaborate on minimizing hallucinations through strong prompt engineering model validation and workflow optimization via advanced data curation alignment and labeling. 

Integrate tools like LlamaIndex and LangChain for hands-on prompt engineering model validation and workflow automation in data curation and alignment processes. 

Work with cross-functional teams (e.g. data scientists product managers) to deploy production-ready AI systems ensuring scalability compliance and explainability. 

Stay updated on emerging AI trends and contribute to internal knowledge sharing such as workshops on best practices for RAG and prompt optimization. 

Required Qualifications  Bachelors or Masters degree in Computer Science AI Data Science or a related field (or equivalent experience). 

3 years of hands-on experience in generative AI LLM development or knowledge retrieval systems.  Proficiency in RAG frameworks vector databases (e.g. Pinecone FAISS for embedding and indexing) and context management to build adaptive knowledge retrieval pipelines. 

Hands-on experience with prompt engineering model validation using tools like LlamaIndex and LangChain and workflow optimization via data curation and alignment. 

Knowledge of embedding models (e.g. OpenAI Cohere) and strategies for chunking indexing and hybrid search. 

Strong skills in prompt engineering model validation to minimize hallucinations and workflow optimization using advanced data curation alignment and labeling. 

Proven ability to conduct A/B testing for prompt efficiency and validate models against curated datasets.  Experience optimizing workflows for data alignment model validation and curation to ensure accurate grounded AI outputs. 

Proficiency in programming languages such as Python; familiarity with SQL and data pipelines is a plus.  Excellent problem-solving skills attention to detail and the ability to work in agile collaborative environments. 

Preferred Qualifications  Experience with additional AI tools like Hugging Face Transformers Elasticsearch or Databricks for large-scale data handling.

  Background in domains like robotics or ADAS is crucial.  Contributions to open-source AI projects or publications in generative AI/RAG.  Familiarity with ethical AI practices bias mitigation and model governance.    If this sounds like the right fit apply now with your resume and a portfolio of relevant projects (e.g. GitHub rep

Qualifications :

B.E

Additional Information :

Exp- 5 years

Remote Work :

No

Employment Type :

Full-time