Leads the team this role joins
In-house, owns the opening
Put the opening up
From your own Gmail and LinkedIn.
How this role compares
One of 19 open AI Engineer roles in IN we are tracking today.
Posted november 2026, with 18 of the others posted since.
Counted across the roles Frontrunner has open right now.
About the role
This is a remote mid-level AI engineering role in India for someone with at least three years of hands-on experience building LLM-based applications and agents. The role is with DCKAP, which connects ERP systems for distributors and manufacturers, and the work is building production AI agents for business and product problems. Engineers are expected to have shipped more than one agent beyond prototypes and to understand tooling, retrieval, memory, evaluation and guardrails.
What you’ll do
- Design and build production AI agents for complex business and product problems, including single and multi-agent systems.
- Build reusable skills, prompts and tools for agents.
- Design retrieval augmented generation and memory strategies for different use cases.
- Build reliable tools and integrations that let agents work with external systems.
- Create evaluation frameworks to measure and improve agent performance.
- Add guardrails, validation and fallback mechanisms.
- Use reflection, feedback and production data to improve agent quality.
- Work with product and engineering teams to bring AI features into production.
What they’re looking for
- Three or more years of hands-on experience building AI agents or LLM applications.
- Experience deploying AI systems in production and building more than one agent beyond tutorials or proofs of concept.
- Understanding of agent architectures, tool calling and multi-agent systems.
- Hands-on work with RAG approaches and memory patterns.
- Experience designing reusable skills, prompts and tools.
- Experience creating evaluations for agent performance and reliability.
- Understanding of guardrails and safe agent behaviour.
- Experience using reflection and feedback loops to improve agents.
- Strong problem solving and the ability to debug non-deterministic systems.
- Willingness to keep learning and experimenting.
- Python, plus an agent framework such as LangGraph, LangChain or similar.
- Experience with an LLM platform such as OpenAI, Anthropic, Gemini or AWS Bedrock.
What’s on offer
- A learning and development budget, with access to courses on Coursera and Stanford Continuing Studies.
- Reimbursement for relevant certifications and workshops.
- A four-day working week during the second week of each month.
- Flexible working hours in a fully distributed workplace, with the option to work remotely from anywhere in the world.
- Maternity and paternity leave.
- Travel to speak at conferences around the world.
- A referral program with a bonus.
Skills
Questions about this role
Is the role remote?
Yes. It is a remote role, and the posting says you can work remotely from anywhere in the world.
How many years of experience are needed?
At least three years of hands-on experience building AI agents or LLM-based applications.
Which tools should I know?
Python, an agent framework such as LangGraph or LangChain, and an LLM platform such as OpenAI, Anthropic, Gemini or AWS Bedrock.