Prompt Engineer
5 days ago
About the Role
We at IDEA Foundation, are seeking a skilled Prompt Engineer with hands-on experience in developing, optimizing, and deploying LLM-driven solutions in production environments. The ideal candidate will have strong expertise in prompt engineering, Retrieval-Augmented Generation (RAG), and AWS AI/ML services, particularly Bedrock, Lambda, and document-processing workflows. The role offers the opportunity to build scalable AI applications and contribute to next-generation automation and knowledge management systems.
Key Responsibilities
- Design, craft, and optimize prompts for generative AI models across diverse use cases, ensuring accuracy, robustness, and reliability in production settings.
- Develop and maintain RAG pipelines, integrating vector stores, embeddings, and retrieval strategies for high-precision LLM outputs.
- Implement and automate AI workflows using AWS services such as:
- Bedrock (Knowledge Bases, Agents, Blueprints, Model Evaluation)
- Lambda for serverless orchestration
- Textract for document extraction
- S3, API Gateway, CloudWatch, IAM, and related services
- Build and deploy end-to-end document-processing solutions using LLMs, OCR, and structured data extraction.
- Collaborate with cross-functional teams to translate business problems into scalable AI-driven solutions.
- Monitor and optimize LLM performance, response quality, latency, and cost.
- Ensure best practices in data handling, prompt versioning, observability, and secure deployment.
- Prepare technical documentation, demos, and communication for internal and client-facing stakeholders.
Required Skills & Qualifications
- Bachelor's/Master's degree in Computer Science, Engineering, Data Science, or related field.
- 3+ years of hands-on experience in prompt engineering or applied generative AI development.
- Proven expertise in designing prompts for LLMs and implementing prompt chaining, tool use, and agent-based workflows.
- Strong understanding of RAG pipelines, vector databases, embeddings, and knowledge bases.
- Experience working with AWS Bedrock, especially Knowledge Bases and Agents.
- Proficiency with AWS services such as Lambda, API Gateway, S3, CloudWatch, Textract, and AWS security/IAM.
- Experience building and maintaining document-processing pipelines combining OCR, extraction, and LLM interpretation.
- Ability to work on production-grade projects with clear evidence of deployments and user adoption.
- Solid programming skills in Python (preferred) or JavaScript/TypeScript.
- Strong communication, documentation, and client-interaction skills.
Job Type: Full-time
Pay: ₹800, ₹1,200,000.00 per year
Work Location: In person
-
Full Stack Architect
2 weeks ago
Panchkula, India Whatjobs IN C2 Full timeRole Overview We are looking for a Full Stack Architect / Lead Engineer with strong hands-on coding and AI solution-building expertise. You will design, build, and scale modern cloud-native applications — leading a small engineering team while contributing directly to architecture, backend, frontend, and AI integrations. Key Responsibilities Lead...
-
Machine Learning Architect
4 days ago
Panchkula, India Grazitti Full timeDescription **Job Description**: We are looking for a Machine Learning Architect with 2-5 years of experience to join our dynamic team. As a Machine Learning Architect, you will be responsible for designing, developing, and deploying machine learning models to address a variety of business challenges. You will work closely with data scientists, software...
-
Lead Developer with Python + Next.js
2 weeks ago
Panchkula, India Advocara Innovation Full timeAdvocara | Tech for Social Impact | Equity + SalaryAdvocara is a mission-driven startup helping people reduce and fight unfair medical bills in the US. This is a very large problem and market opportunity. We combine AI, LLMs, and automation to empower consumers in navigating a complex healthcare system.We have a top-10% team and culture, and seek similar...