AI/ML Engineer

Job Description

Minimum Experience: 5–7 years (Senior AI/ML Engineer)

1. Role Responsibilities

• Develop and deploy fully on-premise AI/ML solutions ensuring strict data privacy

(no external cloud APIs/models).

• Build a secure internal AI chatbot capable of retrieving PDF links, generating

table-format responses, comparing multi-country data, using conversation

memory, and providing autosuggestions.

• Design and implement private RAG pipelines using internal databases,

embeddings, and vector search engines.

• Build and fine-tune self-hosted LLM models .
• Develop an AI translation module that translates PDFs/Word documents while

maintaining exact layout and structure.

• Create a Summary of Changes engine to compare multiple versions of regulatory

documents and detect semantic differences (added/removed/modified

content).

• Implement PDF/Word parsing, OCR, layout extraction, and document

intelligence workflows for structured data generation.

• Develop image comparison components for detecting visual differences in

artwork or label designs.

• Build automated gap analysis, document mapping, and auto-fill systems using

AI-driven content extraction.

• Architect scalable internal AI microservices using FastAPI, secure access

controls, and audit logging.

• Optimize GPU workloads, model training, fine-tuning scripts, and inference

pipelines on-prem.

• Collaborate with regulatory, medical writing, quality, and product teams to

ensure outputs meet pharma documentation requirements.

2. Skills Required

Must-Have Skills

Core AI/ML & NLP

• Strong proficiency in Python and the ML ecosystem.
• Expertise in NLP: tokenization, embeddings, NER, chunking, summarization.
• Advanced hands-on experience with LLMs .
• Prompt Engineering for controlled, structured outputs.
• Deep experience in Model Fine-Tuning (self-hosted models only).
• Strong background with Transformers (HuggingFace).
• Proven experience building RAG pipelines (retrieval, chunking, vector search).
• Strong proficiency with embedding models (SBERT, BERT, LLaMA embeddings).
• Skilled with vector databases: FAISS, ChromaDB.

Document Intelligence & Comparison

• Expertise in PDF extraction: PyMuPDF, PDFMiner, Camelot.
• Strong experience with OCR (Tesseract, PaddleOCR) on-prem.
• Ability to perform document comparison, semantic diff, and advanced

summarization.

• Experience with image comparison and basic computer vision workflows.
• Knowledge of document mapping & gap analysis automation.

Model Deployment & Backend Engineering

• Strong experience with FastAPI for AI microservices.
• Expertise in Linux, Bash, shell scripting, and SSH.
• Strong hands-on experience with Docker & Kubernetes for scalable on-prem

deployment.

• Cloud deployment experience (AWS, Azure, GCP) or on-prem VM deployment —

mandatory for scaling private LLM infrastructure.

• Experience optimizing GPU resources for LLMs and ML pipelines.

Databases & Versioning

• Experience with MongoDB and basic SQL.
• Strong knowledge of Git/GitHub for version control and CI/CD.

Job Types: Full-time, Permanent

Pay: ₹1,000,000.00 - ₹2,000,000.00 per year

Work Location: In person