Agent Engineer

Prodigal; Bengaluru; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Prodigal is hiring a backend/AI engineer to build and deploy LLM-powered AI agents in production, including voice agents, across real-world use cases. You will own the end-to-end lifecycle of AI systems from problem scoping and design to deployment, monitoring, and continuous iteration.

The role requires 1-3 years in backend/data/AI engineering with strong Python and SQL, plus experience with LLMs, RAG, or prompt engineering.

Qualifications

• 1-3 years of backend/data/AI engineering experience.
• Strong in Python and SQL.
• Experience with LLMs, RAG, or prompt engineering.
• High ownership and ability to work in ambiguity and ship fast.

Responsibilities

• Build and deploy LLM-powered AI agents in production.
• Own end-to-end lifecycle of AI systems from design to deployment and monitoring.
• Design and optimize prompts, RAG pipelines, and evaluation frameworks.
• Work with customers and Implementation Managers to understand workflows and drive go-lives and iterations.

Skills

Python

SQL

LLMs

Ownership

Communication

Education

B.Tech/BE/M.Tech in Computer Science

Tools

Databricks

MongoDB

Distributed systems

Job description

Job Summary

Build and deploy LLM-powered AI agents (including voice agents) in production, designed for real-world use cases. Own the end-to-end lifecycle of AI systems - from problem scoping and design to deployment, monitoring, and continuous iteration. Design and optimize prompts, RAG pipelines, and evaluation frameworks to improve accuracy, latency, and reliability. Work directly with customers and Implementation Managers (IMs) to understand workflows, solve real-world problems, and drive successful go-lives and iterations.

Responsibilities

• Build and deploy LLM-powered AI agents (including voice agents) in production, designed for real-world use cases
• Own the end-to-end lifecycle of AI systems - from problem scoping and design to deployment, monitoring, and continuous iteration
• Design and optimize prompts, RAG pipelines, and evaluation frameworks to improve accuracy, latency, and reliability
• Work directly with customers and Implementation Managers (IMs) to understand workflows, solve real-world problems, and drive successful go-lives and iterations

What We're Looking For

• 1-3 years experience in backend / data / AI engineering
• Strong in Python + SQL
• Experience or exposure to LLMs, RAG, or prompt engineering
• High ownership, ability to work in ambiguity and ship fast
• Comfortable working with customers and cross-functional teams

Preferred Qualification

• B.Tech, BE, or M.Tech in Computer Science or a related discipline, with 1-3 years of relevant experience

Bonus

• Experience with production LLM systems / AI agents
• Familiarity with evaluation, agent tooling, or voice AI
• Experience with Databricks, MongoDB, or distributed systems
• Startup or customer-facing engineering experience

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.