Role Summary

Design and build Generative AI capabilities and agentic AI workflows using NLP and Transformer-based models. Develop Retrieval-Augmented Generation (RAG) systems, advanced multi-agent architectures, and production-ready AI services that integrate with enterprise applications and data sources. Ensure solutions are scalable, secure, observable, and cost-efficient while leveraging cloud platforms such as AWS and Azure.

Key Responsibilities

- Design and develop Generative AI services with robust prompting, tool usage, function calling, and workflow orchestration.
- Implement caching, retry mechanisms, token optimization, and cost controls for LLM-powered applications.
- Build and optimize RAG pipelines, including document ingestion, chunking, embedding generation, indexing, reranking, and retrieval quality evaluation.
- Develop advanced agentic AI solutions using multi-tool, multi-step, and multi-agent architectures.
- Apply NLP and Transformer techniques such as fine-tuning, LoRA/adapters, and model distillation based on business requirements.
- Build production-grade Python services and APIs for AI-powered applications.
- Integrate vector databases such as FAISS and Pinecone with frameworks like LangChain and LlamaIndex.
- Implement streaming responses, guardrails, and monitoring for LLM applications.
- Deploy and operate AI solutions on AWS and Azure with solid observability, security, governance, and compliance practices.




- Collaborate with cross-functional teams to integrate AI capabilities into enterprise products and business workflows.

Required Skills

- Strong understanding of Generative AI concepts, including LLMs, embeddings, and prompt engineering.
- Hands-on experience with Transformer models and the Hugging Face ecosystem.
- Expertise in NLP techniques, text processing, and evaluation methodologies.
- Experience designing and implementing RAG systems and advanced agentic AI workflows.
- Strong Python programming skills.
- Experience with AWS and/or Azure cloud platforms.
- Experience building APIs for AI and model-backed applications.
- Familiarity with vector databases such as FAISS and Pinecone.
- Experience with LangChain, LlamaIndex, or similar AI orchestration frameworks.

Qualifications

- Bachelor's, Master's, or equivalent degree in Computer Science, Electrical Engineering, or a related field.
- 4+ years of experience in AI Engineering, Generative AI, NLP, or related domains.

Preferred Skills

- Experience with LLM observability, evaluation frameworks, and guardrails.
- Knowledge of model optimization techniques, inference performance tuning, and cost optimization.
- Experience building scalable, secure, and production-ready AI systems.
- Strong problem-solving skills and the ability to work in cross-functional engineering teams.

Pay: ₹1,800,000.00 - ₹3,000,000.00 per year

Benefits:

- Food provided
- Health insurance
- Internet reimbursement
- Provident Fund
- Work from home

Work Location: Hybrid remote in Bengaluru, Karnataka (Bengaluru Urban District)

📌 Generative and Agentic AI Engineer (India)
🏢 Trinity Soft Solutions
📍 India