AI Engineer - III

Groww; Bengaluru; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Groww is seeking passionate AI Engineers to develop and scale intelligent AI platforms that will enhance user experiences for over 50 million users. In this role, you will design and build end-to-end AI systems, ensuring reliability and compliance.

The ideal candidate has 5–8 years of experience in AI/ML Engineering, strong command in programming languages such as Go, Java, or Python, and hands-on experience with Agentic AI frameworks. This is a thoughtful opportunity to lead technical discussions and mentor engineers while contributing to impactful AI solutions.

Qualifications

• 5–8 years of experience in AI/ML Engineering or related backend engineering roles.
• Hands-on experience with Agentic AI frameworks and orchestration systems.
• Strong knowledge of LLM optimization and latency optimization.

Responsibilities

• Own and scale Groww’s AI platform, driving architecture and reliability.
• Design and build Agentic AI systems end-to-end.
• Monitor and optimize production AI systems for performance.

Skills

AI/ML Engineering

Go

Java

Python

RAG pipelines

System design

Production systems

Mentoring engineers

Open-source contributions

Job description

We’re looking for passionate AI Engineers to build intelligent, scalable, and production-ready AI systems that power impactful user experiences. If you enjoy working on cutting-edge AI/ML technologies, solving complex engineering problems, and shipping real-world AI products, we’d love to talk to you.

What You’ll Do

• Own and scale Groww’s AI platform, driving architecture, reliability, safety, and AI‑powered financial experiences for 50M+ users
• Design and build Agentic AI systems end‑to‑end — from architecture to production deployment
• Develop scalable RAG pipelines with retrieval strategies, embeddings, vector databases, and financial data integrations
• Build reliable backend systems for AI workflows, including tool orchestration, multi‑agent coordination, caching, and session management
• Ensure AI safety and compliance through guardrails, validation layers, fallback handling, and financial policy adherence
• Improve model performance through prompt engineering, evaluation frameworks, and continuous experimentation
• Monitor and optimize production AI systems for latency, reliability, accuracy, and cost efficiency
• Lead technical discussions, mentor engineers, and drive engineering best practices across the team
• Collaborate closely with product, data science, legal, and compliance teams to deliver high‑quality AI solutions at scale

Requirements

• 5–8 years of experience in AI/ML Engineering or related backend engineering roles
• Strong expertise in Go, Java, or Python with experience building scalable distributed systems and backend platforms
• Hands‑on experience with Agentic AI frameworks and orchestration systems including planning, tool execution, retrieval, fallback handling, and multi‑agent workflows
• Deep understanding of RAG pipelines — retrieval strategies, embeddings, vector databases, re‑ranking, and context management
• Strong knowledge of LLM optimization including prompt engineering, evaluation frameworks, latency optimization, and hallucination reduction
• Experience building reliable AI infrastructure with observability, tracing, logging, quality monitoring, and cost optimization
• Strong fundamentals in system design, scalability, resiliency, and performance engineering
• Proven ownership of production systems from architecture to long‑term reliability and scalability
• Ability to mentor engineers, drive technical decisions, and uphold engineering best practices
• Strong execution skills with the ability to operate in fast‑paced and ambiguous environments
• Proactive mindset with a focus on identifying and resolving issues before they impact production
• Contributions to open‑source AI/LLM tooling or internal AI platforms
• Experience building AI evaluation and red‑teaming frameworks
• Understanding of AI safety, prompt injection risks, and adversarial attack mitigation in financial systems