Senior AI/ML Engineer – R01571454

Brillio; Gurugram District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Brillio seeks an experienced AI/ML Engineer to design and implement end-to-end AI agent workflows, focusing on LLM-based applications and RAG systems. You will build and optimize RAG pipelines, experiment with prompt engineering, and ensure reliable production deployments with robust monitoring and quality checks.

Collaboration with data scientists will refine evaluation frameworks and drive measurable performance improvements.

Qualifications

• 2–4 years of experience, including at least 2 years building LLM-based applications, RAG systems, or AI agent workflows.
• Advanced proficiency in Python and hands-on experience with LangChain, LlamaIndex, or similar.
• Expertise in prompt engineering and systematic prompt testing.
• Deep understanding of RAG architectures, including embeddings, vector stores, retrieval strategies, and re-ranking.
• Experience building multi-step agent workflows with tool use, branching logic, and robust error handling.
• Experience with production deployment and monitoring of AI/ML solutions.
• Experience with data pipeline tools and frameworks (KubeFlow, BentoML, Great Expectations, Evidently AI).

Responsibilities

• Design and build end-to-end AI agent workflows, from initial prompt design through production deployment, ensuring scalable and robust solutions
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, including chunking strategies, embedding models, retrieval ranking, and context window management to maximize information accuracy and retrieval efficiency
• Build and systematically iterate on prompt engineering layers, testing and refining prompts and chain-of-thought strategies to achieve consistent, high-quality outputs across diverse inputs
• Implement tool orchestration within agent workflows by integrating agents with databases, rule engines, validation systems, and formatting tools to automate complex tasks
• Establish automated quality checks and validation layers to proactively catch issues and ensure high output reliability before human review
• Instrument solutions for measurement, collaborating with data scientists to develop evaluation frameworks and track solution performance against defined targets
• Deploy and maintain AI/ML solutions in production environments, focusing on reliability, monitoring, and edge case handling
• Design and implement feedback loops that capture expert review data and translate it into measurable improvements in agent performance

Skills

Python

LangChain

LlamaIndex

Prompt engineering

RAG architectures

Embeddings

Vector stores

Agent workflows

Production deployment

KubeFlow

BentoML

Great Expectations

Evidently AI

Education

Bachelors in Computer Science

Certifications in ML/AI

LLM / generative AI certs

Tools

KubeFlow

BentoML

Great Expectations

Evidently AI

Job description

• 2–4 years of experience, including at least 2 years specifically building LLM-based applications, RAG systems, or AI agent workflows

Key Responsibilities:

• Design and build end-to-end AI agent workflows, from initial prompt design through production deployment, ensuring scalable and robust solutions
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, including chunking strategies, embedding models, retrieval ranking, and context window management to maximize information accuracy and retrieval efficiency
• Build and systematically iterate on prompt engineering layers, testing and refining prompts and chain-of-thought strategies to achieve consistent, high-quality outputs across diverse inputs
• Implement tool orchestration within agent workflows by integrating agents with databases, rule engines, validation systems, and formatting tools to automate complex tasks
• Establish automated quality checks and validation layers to proactively catch issues and ensure high output reliability before human review
• Instrument solutions for measurement, collaborating with data scientists to develop evaluation frameworks and track solution performance against defined targets
• Deploy and maintain AI/ML solutions in production environments, focusing on reliability, monitoring, and edge case handling
• Design and implement feedback loops that capture expert review data and translate it into measurable improvements in agent performance

Required Skills:

• Advanced proficiency in Python
• Hands-on experience with LLM frameworks such as LangChain, LlamaIndex, or similar
• Expertise in prompt engineering and systematic prompt testing
• Deep understanding of RAG architectures, including embedding models, vector stores, retrieval strategies, and re-ranking
• Experience building multi-step agent workflows with tool use, branching logic, and robust error handling
• Experience with production deployment and monitoring of AI/ML solutions
• Experience with data pipeline tools and frameworks (KubeFlow, BentoML, Great Expectations, Evidently AI)

Preferred Skills:

• Experience with multi-agent orchestration frameworks
• Background in content generation, translation, or document processing solutions
• Familiarity with fine-tuning LLMs or training reward models
• Experience implementing feedback loops or RLHF mechanisms
• Expertise in LLM cost optimization strategies such as model routing, caching, and prompt compression
• Experience with multi-modal AI systems including voice-to-text, document understanding, and image analysis
• Experience with evaluation frameworks for generative AI, including automated scoring and human evaluation protocols

Desired Qualifications:

• Bachelor’s degree in Computer Science, Data Science, Information Technology, or a closely related discipline
• Certification in Machine Learning or Artificial Intelligence (e.g., TensorFlow Developer Certificate, AWS Certified Machine Learning Specialty)
• Certification in LLM or generative AI technologies (e.g., OpenAI Certified Engineer, Hugging Face Certified AI Practitioner)