AI Engineer

Dreaming big is in our DNA. It’s who we are as a company. It’s our culture. It’s our heritage. And more than ever, it’s our future. A future where we’re always looking forward. Always serving up new ways to meet life’s moments. A future where we keep dreaming bigger. We look for people with passion, talent, and curiosity, and provide them with the teammates, resources and opportunities to unleash their full potential. The power we create together – when we combine your strengths with ours – is unstoppable. Are you ready to join a team that dreams as big as you do? AB InBev GCC was incorporated in 2014 as a strategic partner for Anheuser-Busch InBev. The center leverages the power of data and analytics to drive growth for critical business functions such as operations, finance, people, and technology. The teams are transforming Operations through Tech and Analytics. Do You Dream Big? We Need You.

Job Description Job Title: AI Engineer

Location: Bangalore (Onsite)

Reporting to: Senior Manager - AI Engineering

PURPOSE OF ROLE The AI Engineer will be a hands-on individual contributor responsible for building, reviewing, and delivering complex GenAI solutions for Insights Copilot and related enterprise AI products. The role requires strong engineering ownership, the ability to use AI tooling efficiently for rapid prototyping and development, and close collaboration with principal engineers to convert ambiguous business problems into reliable, scalable, production-ready solutions.

KEY TASKS AND ACCOUNTABILITIES • Build & deliver complex GenAI solutions across LLMs, RAG, agentic workflows, real-time processing and enterprise integrations. • Use AI-assisted development tools efficiently to accelerate rapid prototyping, solution design, code generation, debugging, testing and delivery without compromising engineering quality. • Review pull requests for code quality, architecture alignment, performance, reliability, security, maintainability, and adherence to engineering standards. • Mentor junior engineers by providing technical guidance, structured feedback, pairing support, and practical examples of high-quality AI engineering practices. • Work closely with principal engineers to align solution architecture, implementation choices, technical trade-offs, and delivery plans. • Own delivery of assigned workstreams from design through implementation, testing, deployment support, and production stabilization. • Design and implement LLM-powered applications using LangChain, LangGraph, and agentic patterns such as ReAct, ReWOO, and LLMCompiler. • Develop multi-modal RAG systems and optimize chunking, clustering, retrieval, and context-management strategies for large-scale enterprise data. • Build scalable APIs using FastAPI and integrate AI services with enterprise applications, databases, and orchestration layers. • Implement low-latency inference and deployment patterns using parallel tool calling, caching, and efficient orchestration for interactive AI use cases. • Apply advanced prompt engineering, LLM-as-judge evaluation, self-reflection prompting, prompt compression, and quality measurement techniques. • Collaborate with product, data, platform, and business stakeholders to ensure AI solutions meet functional needs and delivery commitments.

QUALIFICATIONS, EXPERIENCE, SKILLS Education: • Bachelor's or Master's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, Machine Learning, or a related field; equivalent practical experience will also be considered.

Experience: • Minimum 6 to 9 years of experience in software engineering, AI engineering, machine learning engineering, data engineering, or a related technical field. • Hands-on experience delivering production-grade AI applications, LLM workflows, RAG systems, AI APIs, or agentic solutions. • Experience reviewing code, mentoring junior engineers, and contributing as a senior individual contributor in complex engineering environments. • Experience collaborating with principal engineers, architects, product teams, and platform teams to deliver scalable technical solutions.

Technical/Functional Skills: Mandatory Skills: • Efficient use of AI tooling for rapid prototyping, development, debugging, and testing --

Expert • Engineering ownership as a hands-on individual contributor --

Expert • Pull request review, code quality governance, and engineering best practices --

Advanced • Mentoring junior engineers and providing technical guidance --

Advanced • Large Language Models and LLM application development --

Advanced • LangChain and LangGraph --

Advanced • Agentic patterns such as ReAct, ReWOO, and LLMCompiler --

Advanced • Multi-modal RAG, retrieval optimization, and context window management --

Advanced • FastAPI-based API development for AI model serving and enterprise integration --

Advanced • Natural language to SQL and database query optimization --

Intermediate to Advanced • Docker and containerized AI services --

Intermediate to Advanced • Low-latency inference, parallel tool calling, caching, and orchestration architectures --

Intermediate to Advanced • Prompt engineering, LLM-as-judge evaluation, and self-reflection prompting --

Advanced Preferred (Good to have) Skills: • Working with principal engineers on architecture decisions and technical trade-offs --

Advanced • AI response caching, semantic caching, and cache invalidation strategies --

Intermediate • Prompt compression and optimization tools such as LLMLingua, AdaFlow, TextGrad, and DSPy

Intermediate • Service orchestration tools for deployment and operations -

Intermediate • Performance benchmarking, evaluation frameworks, and AI quality measurement -

Intermediate And above all of this, an undying love for beer! We dream big to create a future with more cheers.