Associate Software Engineer
Duck Creek Technologies
Bengaluru, Karnataka, India0–2 yrsJust nowvia LinkedIn
This job at a glance
- Who can apply
- Freshers and up to 2 years · B.Tech / B.E. or M.Tech
- Must know
- PythonGitMachine learning
- Nice to have
- LLMsData structures & algorithmsFlaskFastAPI
- Work
- Hybrid in Bengaluru
- Pay
- Not stated by the employer.
- Skill demand
- Python37%Git34%LLMs9%Machine learning7%of 114 similar fresher jobs posted in India this week
- Listed
- 30 Oct 2026 · still open
Sign in free to see which of these skills your resume already shows.
About the Role
Duck Creek Technologies is hiring early-career engineers to join an AI engineering team building LLM-based systems. This role focuses on evaluating the correctness of AI/LLM system output and modeling extracted information as structured knowledge.
Key Responsibilities
- Build and extend LLM evaluation harnesses (golden datasets, precision/recall/F1, calibration, LLM-as-judge scoring).
- Design and work with knowledge graphs (entity-relationship modeling, graph traversal/queries, embeddings-based similarity and retrieval).
- Build GenAI/LLM pipelines in Python (prompting, RAG, structured output).
- Write clean, tested code; collaborate with senior engineers; document your work.
- Act in accordance with Duck Creek Technologies' mission, vision, and core values.
Requirements & Tech Stack
- Python fundamentals.
- Solid grasp of data structures & algorithms.
- Working understanding of LLM fundamentals: prompting, embeddings, RAG, basic evaluation concepts.
- A maintained personal GitHub profile with at least one substantive AI/LLM project (academic or personal).
- Share your resume along with your GitHub profile link. Applications without a working GitHub link showing original project work will not be considered.
Qualifications
- B.Tech/M.Tech with an AI/ML specialization, or CS/IT with strong, demonstrable AI coursework/projects.
- 0 to 2 years of experience.
Good To Have
- Exposure to evaluation frameworks/metrics for generative AI (e.g., Ragas, DeepEval, or a self-built LLM-judge approach).
- Exposure to knowledge graphs / graph data structures (NetworkX, Neo4j, RDF/OWL, or a well-reasoned custom graph model).
- Any agent framework (LangChain/LangGraph or similar), vector databases, any cloud platform, REST API basics (FastAPI/Flask).
Location & Ways of Working
- This role is aligned to a specific location.
- Expected to reside within reasonable proximity to that location.
- Work may initially be performed remotely, subject to business needs.
- May transition to a hybrid work arrangement, including working from a designated office on a schedule determined by your leader.