Senior Gen AI Engineer

Role & responsibilities

• Design, prototype, and deploy AI-driven applications leveraging LLMs (GPT-4, Perplexity, Claude,

Gemini, etc.) and open-source transformer models.

• Lead or co-lead end-to-end AI/GenAI solutions: from data ingestion, entity extraction, and semantic

search to user-facing interfaces.

• Implement RAG (Retrieval-Augmented Generation) architectures, knowledge grounding pipelines,

and prompt orchestration logic.

• Fine-tune transformer models (BERT, RoBERTa, T5, LLaMA) on custom datasets for use cases like:
• Document understanding
• Conversational AI
• Question answering
• Summarization & Topic Modeling
• Integrate LLM workflows into scalable backend architectures with APIs and frontends.
• Work closely with business teams and pharma SMEs to translate requirements into GenAI

solutions.

• Mentor junior engineers and contribute to AI capability development across the organization

Preferred candidate profile

• Degree in Computer Science, Engineering, Data Science, or related field (BE/BTech/MTech/MCA)
• 35 years of hands-on experience in AI/ML/NLP/LLM solution development
• Strong understanding of GenAI, Prompt Engineering, LLM internals, and multi-layered data

architectures

• Exposure to pharma/healthcare domain is a significant plus
• Excellent problem-solving skills, self-learner, and ability to work in cross-functonal teams
• Experience developing new applications within an agile environment preferred
• Ability to work independently and as part of a team
• Exposure to MLOPs will be an added advantage
• Creative mindset and openness to new ideas.
• Ability to work independently as well as in a team.

Tech Stack & Skills Required

• Programming & Libraries: Python, FastAPI, LangChain, Pandas, PyTorch/TensorFlow,

Transformers (HuggingFace), OpenAI SDK

• Data Extraction & Processing: PDFMiner, PyMuPDF, Tabula, PyPDF2, Tesseract OCR, pythonpptx
• Gen AI / LLMs: OpenAI (GPT), Gemini, Perplexity, Cohere, DeepSeek, Mistral, LLaMA, BERT,

RoBERTa, T5, Falcon

• Use Cases: NER, Summarization, QA, Document Parsing, Clustering, Topic Modeling,

QA over docs

• Embedding & Vector Databases: Pinecone, FAISS, ChromaDB
• RAG & Retrieval Pipelines: LangChain, Haystack, custom retrievers
• Frontend/Backend Integration: React (preferred), FastAPI/Flask, REST/GraphQL APIs

Versioning & Deployment:

Git, Docker, CI/CD (basic), cloud knowledge is a plus (AWS/GCP/Azure)