← Lilly Interview Insights

Lilly·Software Engineer·Hiring Manager Screen·Intermediate

IntermediatePending
May 2026

Summary

Interviewed for a Software Developer role focused on Agentic AI and GenAI at Lilly. Round 1 was a 35-minute hiring manager conversation covering RAG, AI agents, tool orchestration, and a few behavioral questions. Cleared that and Round 2 is a 45-minute DSA round coming up, which the poster is actively trying to prep for.

Questions Asked (2)

Q1

Walk me through your project experience with RAG, AI agents, and tool orchestration.

Technical Trade-offsSystem Design
Author's notes

This was basically the whole first round.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Structure your answer around a specific project, clearly separating the RAG pipeline, AI agent design, and tool orchestration layers. Emphasize the trade-offs you made and the outcomes achieved, tying them to the role's requirements.

Pro tip: Quantify the impact of your architecture choices (e.g., latency reduction, accuracy improvement) and be ready to discuss a failure or lesson learned—this shows maturity and depth.

1. Set the Context

Briefly describe the project's goal, your role, and the scale (e.g., users, data volume). This grounds your answer and shows relevance.

2. Explain the RAG Pipeline

Detail your retrieval and generation components: embedding model, vector database, chunking strategy, and how you handled hallucinations or relevance.

3. Describe AI Agent Design

Outline the agent's architecture: planning, memory, and decision-making. Mention frameworks used (e.g., LangChain, AutoGen) and how you ensured reliability.

4. Detail Tool Orchestration

Explain how the agent invokes external tools/APIs, manages state, and handles errors. Highlight any orchestration patterns (e.g., ReAct, function calling).

5. Highlight Trade-offs and Outcomes

Discuss key decisions (e.g., latency vs. accuracy, cost vs. performance) and their impact. End with measurable results and lessons learned.

Key Points to Mention

  • Vector database selection (e.g., Pinecone, Weaviate) and indexing strategy
  • Chunking and embedding techniques for effective retrieval
  • Agent planning and memory management (e.g., ReAct, CoT)
  • Tool integration patterns (e.g., function calling, API orchestration)
  • Error handling and fallback mechanisms in orchestration
  • Evaluation metrics (e.g., retrieval accuracy, task success rate) and iteration

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q2

What DSA topics and problem difficulty should candidates expect in the technical coding round for this role?

Algorithms & Data Structures
Author's notes

This is actually a question the poster is asking the community, not something asked by the interviewer.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by acknowledging that you've researched the typical interview process for software engineering roles at Lilly, then outline the core DSA topics and difficulty levels you expect. Emphasize that you're prepared for a mix of easy to medium problems, with a focus on practical problem-solving and clean code.

Pro tip: Mention that you've practiced explaining your thought process aloud and writing production-quality code, as interviewers at Lilly value communication and maintainability alongside correctness.

1. Acknowledge Research

State that you've looked into the interview process and understand that Lilly's technical rounds typically cover fundamental DSA topics.

2. List Core Topics

Enumerate the key DSA areas such as arrays, strings, linked lists, trees, graphs, sorting, searching, and dynamic programming.

3. Discuss Difficulty

Explain that problems usually range from easy to medium difficulty, with occasional hard problems depending on the role's seniority.

4. Highlight Preparation

Describe how you've prepared by solving problems on platforms like LeetCode and practicing mock interviews.

5. Connect to Role

Relate the DSA topics to real-world software engineering tasks at Lilly, showing how these skills apply to the job.

Key Points to Mention

  • Arrays and strings are frequently tested due to their foundational nature.
  • Trees and graphs are important for roles involving data processing or system design.
  • Dynamic programming and recursion are often used to assess problem-solving skills.
  • Difficulty is typically LeetCode easy to medium, with some hard problems for senior positions.
  • Interviewers value clean, efficient code and the ability to explain your approach.
  • Practicing with timed mock interviews helps simulate the actual experience.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.