Data Scientist

Position Overview

We are looking for an AI Data Engineer with 2+ years of hands-on experience in data engineering, vector databases, LLM/AI integrations, and Python-based automation. The ideal candidate should have strong knowledge of Open AI, AWS Bedrock, embeddings, Flowise, prompt engineering, and building scalable RAG (Retrieval-Augmented Generation) pipelines.

Key Responsibilities:

AI & LLM Integrations

• Integrate and optimize OpenAI, GPT models, AWS Bedrock models (Claude, Titan, etc.) for production workflows.
• Build and maintain Retrieval-Augmented Generation (RAG) systems using vector search.
• Develop prompt engineering strategies, structured prompts, and dynamic contextual prompts.
• Implement LLM orchestration using Flowise, Lang Chain, or Llama Index.

Data Engineering & Pipelines

• Design, build, and maintain ETL/ELT pipelines for structured & unstructured data.
• Develop ingestion workflows for PDFs, docs, images, and text for LLM training and retrieval.
• Implement data cleaning, transformation, preprocessing, chunking, and embedding generation.
• Handle large-scale data pipelines that feed AI models and vector databases.

Vector Database Engineering

• Work with Pinecone, Qdrant, Milvus, We aviate, Chroma to store and retrieve embeddings.
• Optimize vector indexes, similarity search, metadata filtering, and document-versioning logic.
• Manage vector schema design and vector DB performance tuning.

Python Development & Automation

• Build Python-based microservices, APIs (FastAPI/Flask), and automation scripts.
• Create backend functions to handle AI requests, data ingestion, embeddings, and retrieval logic.
• Integrate with cloud storage, messaging queues, and external APIs.

Cloud & DevOps

• Deploy AI and data pipelines on AWS (Lambda, S3, DynamoDB, EC2, API Gateway).
• Manage secrets, IAM roles, scalability, and cloud resource optimization.
• Containerize workloads using Docker and work with CI/CD workflows (GitHub/GitLab).

Cross-functional Collaboration

• Work alongside AI engineers, backend teams, data scientists, and product managers.
• Document workflows, maintain internal knowledge bases, and support debugging across teams.

Required Skills & Qualifications

• Bachelor's degree in Computer Science, Data Science, Engineering, or related field.
• 2+ years of experience in data engineering, AI, or ML-focused development.
• Strong in Python (FastAPI, Flask, Pandas, NumPy, AsyncIO).
• Experience with Open AI, GPT models, AWS Bedrock, embeddings, and tokenization.
• Strong understanding of data preprocessing for LLMs: chunking, cleaning, vectorization.
• Hands-on experience with vector databases: Pinecone, Qdrant, Milvus, We aviate, Chroma.
• Practical experience with Flowise, Lang Chain, or Llama Index.
• Knowledge of prompt engineering and optimizing LLM responses.
• Experience with SQL & NoSQL databases.
• Familiar with API integrations, backend workflows, and cloud-based pipelines.
• Understanding of CI/CD workflows, version control (Git), and containerization (Docker).

Nice-to-Have

• Experience with MLOps tools and model monitoring.
• Exposure to model fine-tuning or supervised generation training.
• Familiarity with Airflow, Prefect, or cloud-native workflow orchestrators.
• Hands-on with parallel processing or distributed pipelines.

Soft Skills

• Strong analytical thinking and problem-solving capability.
• Clear communication and documentation.
• Ability to work in fast-paced, agile environments.
• Quick learner with deep curiosity about AI/ML technologies.

Job Types: Full-time, Permanent

Pay: ₹300, ₹420,000.00 per year

Work Location: In person