Associate Software Engineer
Duck Creek Technologies (company site, opens in a new tab)0–2 yrsBengaluruOn-siteDirect career pageEst. 6–12 LPA
Posted 3d ago
Reach people at Duck Creek Technologies
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 Duck Creek Technologies 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
- Build LLM evaluation harnesses using golden datasets and measures such as precision, recall, F1, calibration, and LLM-as-judge scoring.
- Model extracted information as knowledge graphs, and support graph queries, traversal, and embeddings-based retrieval.
- Develop Python GenAI/LLM pipelines using prompting, RAG, and structured outputs; write tested code and document work.
Minimum Requirements
- Work Experience Required: 0–2 years; B.Tech/M.Tech in AI/ML, or CS/IT with strong, demonstrable AI coursework or projects.
- Strong Python fundamentals, solid data structures and algorithms, and working knowledge of LLM fundamentals including prompting, embeddings, RAG, and basic evaluation.
- A maintained GitHub profile with at least one substantive, original AI/LLM project is mandatory; submit the profile link with the resume. Applications without a working link showing original project work will not be considered.
- Must reside within reasonable proximity to the role’s designated location and may be expected to work hybrid. The specific location is Not explicitly mentioned in the JD.
Ideal Candidate Profile
- Early-career applicant with a demonstrable AI/LLM project and a clear interest in testing whether model outputs are correct—not just building prompts or demos.
- Best fit for someone able to structure extracted information into entities and relationships, and use graphs or retrieval to make it queryable and useful.
- Evaluation frameworks or metrics, knowledge-graph tools, agent frameworks, vector databases, cloud platforms, or REST API experience are advantageous, but not stated as mandatory.