Agentic Systems Engineer
Kantiv (formerly Joist AI)· India
Posted October 2, 2026
- Experience
- 2 – 4 years
- Pay
- Not disclosed
- Education
- Not specified
- Location
- India
- Work mode
- On-site
- Job type
- Full-time
About this role
Kantiv (Joist AI) builds AI-powered software for marketing and revenue operations in the architecture, engineering and construction industry. This engineer builds agentic applications that streamline proposal writing, covering multi-agent orchestration, memory, tools and evals.
What you will do
- Build agents as modular, plug-and-play components
- Add short-term, long-term and retrieval-backed memory layers
- Wire up tool integrations, MCP servers and skills
- Own feature quality through tests, evals and observability
- Analyze production traces and fix issues
What the employer expects
- 2-4 years of production software
- Strong, clean Python
- Grounding in RAG, prompting patterns, tool use, structured outputs and context management
- Built something non-trivial with modern agent tooling
- Hands-on Langfuse, LangSmith or similar tracing
- Data-driven, detail-oriented problem solving
- Search/retrieval, LLM evals and LangGraph experience a plus
Skills
- Python
- LangGraph
- RAG
- MCP
- Langfuse
- LangSmith
- Embeddings
- Vector databases
- LLM evaluations
Apply on the employer's site
The application opens on Kantiv careers page (Ashby). Dev Portal Notes does not collect your application or charge a fee.
Know someone who fits this role?
Applications are handled on the employer's own site.
Prepare for this role
Close the skill gap
Become an AI Engineer: LLMs, RAG and Agents
Learn to build with large language models: prompting, fine-tuning, RAG and agents, in working code.
Get the courseThe Python Mega Course
Python taught by building real applications, from scripting through web apps and data work.
Get the courseSome links on this page may generate a small commission at no extra cost to you.