Senior AI / GenAI Engineer (Advanced RAG & Agentic AI)

Trigent Software; Chennai District; On-site; INR 900,000 - 1,300,000; Full time

Job summary

Trigent Software is seeking a Senior AI/GenAI Engineer in Chennai to design, develop, and deploy enterprise-scale GenAI solutions. The role emphasizes Advanced RAG architectures, agentic AI, and LLM orchestration, with production-grade deployment and end-to-end responsibility from experimentation to production.

Strong hands-on experience with LLMs, prompt engineering, and model benchmarking is required. Knowledge of Snowflake is desirable.

Qualifications

• Strong hands-on experience with LLMs and Generative AI application development.
• Prompt engineering, optimization, and evaluation frameworks.
• BBenchmarking, accuracy evaluation, hallucination assessment, and model monitoring.
• Experience with OpenAI, Azure OpenAI, Anthropic, Llama, Mistral, or similar models.

Responsibilities

• Design and build enterprise GenAI solutions using advanced RAG techniques.
• Develop scalable AI applications and AI agents for business use cases.
• Optimize retrieval pipelines for accuracy, latency, and cost.
• Perform prompt engineering, evaluation, and model performance testing.
• Collaborate with stakeholders to translate requirements into AI solutions.
• Implement governance and monitoring for AI applications.
• Support production deployments and continuous improvement.
• Mentor junior engineers and contribute to AI best practices.

Skills

Generative AI

LLMs

Prompt engineering

OpenAI/Azure OpenAI

Agentic AI

LLM benchmarking

Vector databases

Python

REST APIs

SQL

Git / CI/CD

MLOps

Education

Bachelor's or Master's in CS/AI

Tools

Pinecone

Weaviate

FAISS

Chroma

Azure AI Search

Job description

Senior AI / GenAI Engineer (Advanced RAG & Agentic AI)

NOTE : Min 5+ years of Exp and Candidate has to be from Chennai

Only Immediate joiners

Role Overview

We are seeking a highly skilled Senior AI / GenAI Engineer to design, develop, and deploy enterprise-scale Generative AI solutions. The ideal candidate should possess strong hands‑on experience in Advanced Retrieval-Augmented Generation (RAG) architectures, Agentic AI systems, LLM orchestration frameworks, and production‑grade AI applications. The role requires expertise in translating business requirements into scalable AI solutions and driving end‑to‑end implementation from experimentation to production.

Knowledge of Snowflake and related cloud data platforms is desirable but not mandatory.

Mandatory Skills

Generative AI & LLMs

• Strong hands‑on experience with Large Language Models (LLMs) and Generative AI application development.
• Experience with prompt engineering, prompt optimization, and evaluation frameworks.
• Expertise in LLM benchmarking, accuracy evaluation, hallucination assessment, and model performance monitoring.
• Experience working with OpenAI, Azure OpenAI, Anthropic, Llama, Mistral, or similar foundation models.

Advanced RAG (Mandatory)

• Extensive experience designing and implementing Advanced RAG architectures.
• Hands‑on expertise in:
  • Hybrid Search (Vector + Keyword Search)
  • Semantic Search
  • Metadata Filtering
  • Parent-Child Retrieval
  • Multi-Vector Retrieval
  • Context Compression
  • Re-ranking Techniques
  • Query Expansion and Query Transformation
  • Knowledge Graph-based Retrieval
  • Adaptive / Agentic RAG
  • Multi-hop Retrieval
  • Citation and Grounded Response Generation
• Experience with vector databases such as Pinecone, Weaviate, Chroma, FAISS, Azure AI Search, or similar platforms.
• Experience evaluating retrieval quality using Precision@K, Recall@K, MRR, NDCG, and related metrics.

Machine Learning & NLP

• Strong understanding of Machine Learning and Natural Language Processing concepts.
• Experience in model development, feature engineering, model evaluation, and production deployment.
• Familiarity with classification, forecasting, prediction, and optimization use cases.

Programming & Development

• Strong proficiency in Python.
• Experience with REST APIs and microservice‑based architectures.
• Experience working with SQL databases and data processing pipelines.
• Familiarity with Git, CI/CD, testing frameworks, and MLOps practices.

Preferred Skills

Snowflake (Optional)

• Experience with Snowflake architecture and data warehousing concepts.
• Exposure to Snowflake Cortex, AI functions, and cost optimization.
• Understanding of data processing pipelines, warehouse sizing, and performance tuning.

Cloud Platforms

• AWS(Preferred)
• GCP

Key Responsibilities

• Design and develop enterprise GenAI solutions leveraging advanced RAG techniques.
• Build scalable AI applications and AI agents for business use cases.
• Develop and optimize retrieval pipelines for accuracy, latency, and cost.
• Conduct prompt engineering, evaluation, and model performance testing.
• Collaborate with business stakeholders to understand requirements and translate them into AI solutions.
• Implement monitoring and governance controls for AI applications.
• Support production deployments and ongoing model improvements.
• Mentor junior engineers and contribute to AI best practices.

Educational Qualifications

• Bachelor's or Master's degree in Computer Science, Data Science, Artificial Intelligence, Engineering, or a related field.

Nice-to-Have Experience

• Text-to-SQL applications.
• Enterprise document intelligence solutions.
• AI governance and model risk management practices.
• LLM observability tools such as LangSmith, TruLens, Arize Phoenix, or similar.
• Knowledge of financial services, insurance, or enterprise operations domains.