Senior Software Developer (AI Agents)

nCircle Tech Co; Pune District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

nCircle Tech Private Limited invites a Senior Software Engineer to join the Data + Automation team. You will design, build, and ship production services including LLM-powered agents, with a focus on reliability and scalability in Python and Node/TypeScript.

You'll deploy on AWS using IaC, manage CI/CD pipelines, and contribute to a shared codebase within a Databricks-powered platform. This hands-on role suits engineers who thrive in fast-moving AI-enabled environments.

Qualifications

• 5+ years software engineering experience.
• Proficiency in Python and Node/TypeScript.
• Experience building production-grade LLM agents.
• Hands-on AWS and IaC (Terraform/CDK).
• Experience with Databricks and Delta Lake.

Responsibilities

• Design, build, and productionize LLM agents and tool-use loops.
• Develop production services and APIs in Python and TypeScript.
• Deploy and operate on AWS with IaC and CI/CD pipelines.
• Contribute to a shared codebase with code reviews and commits.

Skills

Python

Node/TypeScript

AWS

Databricks

Terraform

LLM Agents

CI/CD

Delta Lake

Job description

nCircle Tech Private Limited (Incorporated in 2012) empowers passionate innovators to createimpactful 3D visualization software for desktop, mobile and cloud. Our domain expertise in CADand BIM customization is driving automation with the ability to integrate advanced technologieslike AI/ML and AR/VR, which empowers our clients to reduce time to market and meet businessgoals. nCircle has a proven track record of technology consulting and advisory services for AECand Manufacturing industry across the globe. Our team of dedicated engineers, partnerecosystem and industry veterans are on a mission to redefine how you design and visualize.

Job Description

ABOUT THE ROLEThe Data + Automation team at nCircle Tech builds the data and automation infrastructure behind decisionmaking across the business. Our platform runs on Databricks and AWS. We're hiring a strong softwareengineer to design, build, and ship production services — including LLM-powered agents and the toolingaround them. This is a hands-on, code-first role.

WHAT YOU'LL WORK ON

• Designing, building, and productionizing LLM agents: tool-use loops, retrieval, orchestration,evaluation, and guardrails
• Writing the production-grade services and APIs around those agents in Python and Node/TypeScript
• Deploying and operating on AWS — provisioning with IaC, wiring CI/CD, owning your code fromcommit to production
• Contributing to a shared codebase with feature branches, code review, and Conventional Commits

REQUIRED

Software Engineering (the core)

• Strong Python and Node/TypeScript — writes clean, tested, production-grade code, not scripts
• Feature branches and PRs; comfortable both giving and receiving code review; meaningful commitmessages
• Follows engineering standards (12-factor, testing, documentation) without hand-holding

AWS + IaC

• Real AWS experience — the environment our services run on
• Deploys with Infrastructure as Code (Terraform, CDK, or equivalent) rather than clicking throughconsoles
• Comfortable with CI/CD, environment promotion, and AWS basics (S3, IAM, networking)

LLM Agents (non-negotiable)

This is a hard requirement, not a nice-to-have. We are a small team and cannot train this skill on the job— you must already know how to build agents and be able to contribute to real work quickly.

• Has built and shipped LLM agents to production — not demos or prototypes; systems that ran andwere relied on

Can explain the agent loop from experience: how the model decides to call a tool, observes the result,and re-decides across multiple steps1Senior Software Engineer, AI Agents

Has designed retrieval (RAG) end-to-end — chunking, indexing, hybrid or re-ranked retrieval — andcan justify each choice

Has a real evaluation story: how they measured whether the agent was correct, and the worst failuremode they hit in production and fixed

Knows when NOT to use an agent — where a plain LLM call or deterministic code is the better answer

Framework-agnostic — LangChain, CrewAI, Databricks Agent Framework, or raw tool-use loops allfine; what matters is that you've shipped real agents

Our platform runs on Databricks, so this is required — but working proficiency, not mastery. You shouldbe able to build and ship in Databricks unaided; you don't need to be a Spark-tuning specialist.

• Comfortable building and running Databricks notebooks and Jobs (task chains, parameters,schedules) end-to-end
• Understands the Unity Catalog three-part namespace (catalog.schema.table) and works within it
• Has written Delta Lake operations beyond basic reads — e.g. MERGE, overwrite, schema evolution
• Can navigate and debug an existing pipeline, not only write greenfield code

GOOD TO HAVE

• Deeper Databricks / Spark depth — performance tuning, advanced Unity Catalog governance
• Agent observability and tracing tools in production
• Construction, AEC, or project-based industry experience
• Jira

GENERAL BAR

• 5+ years writing code, not configuring tools
• Ships independently: scopes work, executes, communicates progress
• Can ramp on an unfamiliar system by reading docs and asking targeted questions