Generative AI Engineer

Flexible schedule
 
Full job description
About Us

We are a cutting-edge AI-first company focused on building scalable, ethical, and intelligent systems to transform how humans interact with digital information. We’re developing an enterprise-grade generative AI solution that leverages the latest in Amazon and Anthropic technologies to revolutionize decision-making and automation across industries.

Job Summary

We are looking for a hands-on Generative AI Engineer with deep expertise in Amazon Bedrock, Amazon Q, Amazon Textract, and Anthropic Claude. You will lead the design, development, and deployment of LLM-powered solutions using state-of-the-art tools and APIs to build secure, reliable, and explainable AI systems for enterprise use.

Key Responsibilities

Architect and build generative AI pipelines using Amazon Bedrock and Anthropic Claude (via APIs or SDKs).
Integrate Amazon Textract for intelligent document processing and data extraction.
Build knowledge retrieval and synthesis workflows using Amazon Q and vector databases for RAG (Retrieval Augmented Generation).
Develop reusable prompt templates, fine-tuning strategies, and orchestration logic for large-scale generative AI use cases.
Collaborate with DevOps teams to deploy models using AWS Cloud (Lambda, S3, EC2, SageMaker, etc.).
Ensure data privacy, compliance, and governance standards are met.
Conduct performance tuning, cost optimization, and observability enhancements across all deployed AI services.
Contribute to the evaluation of emerging tools (e.g., LangChain, Haystack, etc.) and foundational models for integration.
Required Skills and Qualifications

Bachelor’s or Master’s in Computer Science, AI, Data Science, or a related field.
4+ years of experience in software engineering or ML/AI development.
Strong hands-on experience with:
Amazon Bedrock (e.g., invoking Claude, Titan, or third-party models)
Anthropic Claude API (prompt design, context management, response parsing)
Amazon Textract (for OCR, form, and table data extraction)
Amazon Q (knowledge assistant and RAG integrations)
AWS Cloud Services (IAM, Lambda, S3, API Gateway, DynamoDB, SageMaker)
Solid understanding of LLM architecture, prompt engineering, and fine-tuning techniques.
Familiarity with Python, REST APIs, JSON, and asynchronous workflows.
Preferred Qualifications

Experience with vector databases (e.g., Pinecone, Weaviate, FAISS) and embeddings.
Working knowledge of LangChain, Haystack, or other LLM orchestration frameworks.
Prior experience building secure, scalable AI applications in production environments.
Understanding of ethical AI, model explainability, and data privacy regulations (GDPR, HIPAA, etc.).
What We Offer

Competitive salary and performance-based bonuses
Remote-friendly work environment with flexible hours
Access to premium tools, APIs, and cloud credits
Opportunity to work at the forefront of applied AI with global impact
Supportive and highly skilled cross-functional team
To Apply

Send your updated CV, GitHub/portfolio links, and a short cover letter highlighting your experience to [surbhi.mehta@thesaffronsolution.com] and [pradeep.gopalsamy@thesaffronsolution.com]
Job Type: Full-time

Benefits:

Work from home
Schedule:

Monday to Friday
Night shift
Application Question(s):

Do you hold any relevant certifications (e.g., AWS Certified Machine Learning – Specialty, Generative AI on AWS, other cloud/AI certifications)?
Have you worked with Amazon Textract, Amazon Q, Amazon SageMaker, AWS Lambda, Amazon API Gateway, Amazon DynamoDB?
Experience:

hands-on experience with Amazon Bedrock: 4 years (Required)
Work Location: Remote

Expected Start Date: 01/08/2025