EXL - GenAI Engineer - LLM/RAG

Role & responsibilities :

- Manage GenAI models production pipelines to debug defects and provide root cause assessments.

- Build and orchestrate LLM-based workflows using frameworks such as LangChain, including prompt engineering and pipeline design.

- Implement Retrieval-Augmented Generation (RAG) architectures leveraging vector databases such as Pinecone for semantic search and contextual retrieval.

- Work with document ingestion and extraction workflows, including processing unstructured documents (PDFs, scans, forms) using tools like AWS Extract and GenAI-based extraction techniques.

- Collaborate with cross-functional teams (engineering, product, and business stakeholders) to define data requirements, evaluation metrics, and success criteria.

- Communicate findings and insights effectively to both technical and non-technical audiences through visualizations, reports, and presentations.

- Stay current with industry trends, tools, and best practices in Generative AI, LLMs, data science, and analytics.

- Mentor junior team members and contribute to a culture of continuous learning and technical excellence.

Qualifications :

- Bachelors or Masters degree in Data Science, Computer Science, AI/ML, Statistics, Mathematics, or a related field.

- 3 to 6 years of experience in a data science, applied ML, or GenAI role, with a strong portfolio of projects.

- Hands-on experience with machine learning frameworks (scikit-learn, TensorFlow, PyTorch).

- Practical experience with LLMs, GenAI frameworks, LangChain, and prompt-driven workflows.

- Strong understanding of RAG patterns, vector embeddings, and vector databases such as Pinecone.

Preferred candidate profile :

- Experience with big data technologies such as Spark or Hadoop.

- Familiarity with deploying ML and GenAI solutions on cloud platforms (AWS).

- Palantir Experience is an added advantage

- Exposure to productionizing LLM pipelines, monitoring, and evaluation.

- Domain experience in finance, insurance, healthcare, or other data-intensive industries.