Full Stack Software Engineer, India
Doxel (company site, opens in a new tab)4+ yrsBengaluruHybridDirect career pageEst. 18–30 LPA
Posted 3d ago
Reach people at Doxel
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Doxel you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own and improve a production LLM agent that maps construction schedule activities to elements in 3D building models, aiming to shift analysts from correcting results to validating them across hundreds of projects.
- Build evaluation and operational controls, including precision/recall tracking, regression checks, run budgets, caching, retries, and tracing; use analyst corrections to improve accuracy.
- Deliver job-management, review, and analyst-training tools in Python and TypeScript, while partnering with analysts and product, BIM, data, and 3D teams; mentor engineers in India.
Minimum Requirements
- Work Experience Required: 4+ years of professional software engineering in TypeScript and Python, including ownership of production systems.
- Hands-on experience building LLM agents or LLM-backed applications for real users, including tool calling, structured outputs, and prompt/context design; experience measuring output quality against ground truth.
- Full-stack capability across APIs, data pipelines, and web apps; solid backend fundamentals including async/concurrent programming, SQL and relational data modeling, retries, and idempotency.
- Experience with cloud platforms, containers, CI/CD, and workflow orchestration; GCP is preferred.
Ideal Candidate Profile
- Has taken LLM features into production and uses evaluation results and expert review feedback to guide changes and releases.
- Can work across backend systems, data workflows, and operations-facing tools, with attention to reliability, cost, and traceability.
- Experience with human-in-the-loop review, retrieval/search, agent harnesses, or construction/BIM/3D/scheduling domains is a relevant advantage.