AI Engineer
Experience: 3–6 Years
Employment Type: Contract
Project Duration: 3 Months
Background: Bioinformatics / Computational Biology / Life Sciences
Role Summary
We are looking for an AI Engineer with a Bioinformatics/Life Sciences background to develop AI-assisted data exploration capabilities over curated scientific datasets.
The role will focus on applying LLM/Generative AI and natural-language querying to Bioinformatics and scientific data, with exposure to the Databricks ecosystem.
Key Responsibilities
    • Develop AI/GenAI capabilities for natural-language exploration of scientific and Bioinformatics datasets.
    • Implement NL-to-SQL use cases over curated Databricks Gold datasets.
    • Configure and evaluate Databricks AI/BI Genie or equivalent capabilities.
    • Develop prompts, semantic context and metadata to improve query accuracy.
    • Build Python-based AI/LLM components and integrations.
    • Implement appropriate guardrails, grounding and validation for AI-generated queries and responses.
    • Validate AI-generated SQL and results against underlying datasets.
    • Work with the Data Architect, Data Engineer and Bioinformatics SME to understand scientific data and user queries.
    • Support integration of AI capabilities with Databricks data products.
    • Develop test cases and evaluate AI responses for accuracy, relevance and consistency.
    • Support documentation, demonstrations and UAT.
Must Have
    • 3+ years of AI, Data engineering experience.
    • Strong Python and SQL skills.
    • Hands-on experience with LLMs / Generative AI.
    • Experience developing LLM-based applications or NL-to-SQL solutions.
    • Understanding of prompt engineering, grounding and LLM evaluation.
    • Bioinformatics/Life Sciences background or project experience.
    • Working knowledge/exposure to Databricks and modern data platforms.
    • Ability to work with structured scientific/analytical datasets.
Preferred
    • Databricks AI/BI Genie experience.
    • Experience with genomics, biomarker or multi-omics data.
    • Experience with RAG and enterprise GenAI solutions.
    • Exposure to AWS AI/ML services.
    • Databricks certification.