Director - GenAI Application Engineering
Description
Director: Highly skilled GenAI Application Leader with 15+ years of total experience who can drive the design, development, testing, and deployment of Generative AI-based applications focused on Data and Analytics in the Life Sciences domain.
The ideal candidate will have a strong background in Python, RAG, knowledge graphs, Gen AI/LLM frameworks (LangChain, LangGraph), AWS/Azure cloud services with hands-on experience integrating and fine-tuning GPT, Anthropic Claude, Mistral, or Snowflake Cortex for real-world business use cases.
Job Responsibilities:
Solution Architecture & Design:
- Lead the end-to-end architecture and design of Generative AI applications.
- Drive solution and architecture discussions with client teams using LLMs, Retrieval-Augmented Generation (RAG), and Knowledge Graphs for structured and unstructured data sources.
- Understand business requirements and guide teams to build modular AI workflows, ensuring scalability, security, and performance.
- Evaluate and recommend GenAI frameworks/tools (LangChain, LangGraph, Semantic Kernel, etc.).
- Collaborate with data engineers and pharma domain experts to design semantic data models and context-aware knowledge bases.
Leading Gen AI Application Development & Engineering Teams:
- Drive full-stack design and development using Python (FastAPI, Flask) and React/Next.js for GenAI-powered frontends.
- Drive teams building microservices or API layers that expose AI functionalities securely.
- Design user-centric applications that embed GenAI outputs seamlessly into custom UI or enterprise BI tools like Power BI.
- Work with data engineering and analytics teams to connect GenAI apps to existing data ecosystems (AWS S3, Azure Data Lake, Snowflake, Databricks, etc.).
- Drive usage of knowledge graphs and metadata-driven approaches to enhance contextual reasoning and data discovery.
AI Model Integration & Fine-tuning:
- Drive the integration of LLMs (OpenAI GPT, Anthropic Claude, Mistral, Snowflake Cortex, etc.) into enterprise-grade applications.
- Fine-tune or prompt-tune foundation models using domain-specific data (commercial, patient, Omni-channel, clinical, or market access data).
- Design and implement RAG architectures leveraging vector databases (ChromaDB, Pinecone, FAISS, Weaviate, etc.).
- Develop prompt engineering frameworks and guardrails to ensure factuality, interpretability, and compliance.
- Establish evaluation pipelines for model performance, accuracy, latency, and hallucination detection.
Leadership & Collaboration:
- Drive Gen AI use cases relevant to BIM practice (focused on data management and analytics).
- Lead a cross-functional GenAI development team of engineers, business analysts, data scientists, and UI developers.
- Stay ahead of the curve with emerging LLM architectures, multi-agent systems, and reasoning frameworks to provide technical guidance.
- Drive knowledge-sharing sessions and PoCs to evangelize Generative AI adoption across the organization.
Education:
- BE/B.Tech
- Master of Computer Application
Skills
- AI
- Ai Enablement
- Analytics
- Anthropic
- API
- AWS
- Azure
- BIM
- ChromaDB
- Claude
- Cloud
- Data Engineering
- Data Lake
- Databricks
- FAISS
- FastAPI
- Fine Tuning
- Flask
- Generative AI
- LangChain
- LangGraph
- LLM
- Microservices
- Mistral
- Next.js
- OpenAI
- Pinecone
- Power BI
- Prompt Engineering
- Python
- RAG
- React
- S3
- Semantic Kernel
- Snowflake
- Vector Databases
- Weaviate
Sign in to read and join the discussion.