# Interview — Senior Java Backend Engineer

- **Difficulty**: hard
- **Started**: 2026-04-28T06:16:09.216Z
- **Ended**: 2026-04-28T06:17:26.716Z
- **Target**: 2 questions / 2 min

## Score: 1.2 / 10 — _strong-no-hire_

### Dimensions
- Technical depth: 1/10 — When asked to explain a specific N+1 query issue listed on her own resume, the candidate responded 'I don't remember what exactly I did there, but it was a complicated problem' — zero technical content was offered.
- System design: 1/10 — The interview was terminated after one question with no substantive candidate response; no system design content was demonstrated at any point.
- Communication: 1/10 — The candidate's only substantive response opened with an irrelevant audio comment and concluded with 'it was a complicated problem' — no attempt to structure or reason through the question was made.
- Role fit: 2/10 — Resume describes plausible high-traffic production systems at HP and MahaRERA with PostgreSQL and Spring Boot, but the candidate could not recall a single specific technical decision from that work when probed.

### Strengths
- Resume describes a state-machine-based subscription lifecycle at HP using the State design pattern with strict transition validation — indicates at least some design thinking at some point.
- Resume claims Resilience4j circuit breaker configuration with specific parameters (failure thresholds, open/half-open state transitions, fallback handlers), suggesting some familiarity beyond surface-level usage.
- MahaRERA work references concrete performance-related actions: N+1 resolution, Spring Cache for master data, and HikariCP tuning — suggesting exposure to production performance concerns even if not articulable under interview conditions.
- Eight years of claimed production experience across four distinct employers and domains provides a plausible foundation, even if entirely unverified in this session.

### Weaknesses
- Failed to recall or articulate any detail about N+1 query resolution — a bullet point on her own resume, and arguably the most basic JPA performance concept expected of a senior engineer.
- Opened her only answer with an unrelated audio comment, signalling poor preparation and an inability to maintain composure when asked a pointed technical question.
- Offered no attempt to reason through the topic even partially — 'it was a complicated problem' with no follow-on is a disqualifying signal for a role requiring end-to-end service ownership.
- Kafka is completely absent from the resume and interview despite being an explicit JD requirement; this is a significant gap for a senior microservices role.
- Kubernetes is not present on the resume at any meaningful level; Docker is listed, but no container orchestration depth is evidenced, leaving a second core JD requirement unaddressed.

### Study plan
- [ ] N+1 detection and resolution in Hibernate/JPA: practice explaining how to identify N+1 via spring.jpa.show-sql, Hibernate statistics, or p6spy; fix with JOIN FETCH, @EntityGraph, or spring.jpa.properties.hibernate.default_batch_fetch_size — be able to show a before/after query count.
- [ ] STAR method for resume-backed answers: for every bullet on your resume, write a 3-sentence structured answer covering the specific context, the exact technical action you took, and the measurable outcome — rehearse these until they are instant recall.
- [ ] Apache Kafka fundamentals: producer/consumer model, consumer groups, partition assignment, offset management, and at-least-once vs exactly-once delivery semantics — treat this as a hard gap that will block you on most senior JDs.
- [ ] Kubernetes core concepts: Pod, Deployment, Service, ConfigMap/Secret, liveness and readiness probes, and Horizontal Pod Autoscaler — be able to describe how a Spring Boot microservice is deployed, configured, and scaled in a cluster.
- [ ] JVM tuning essentials: G1GC vs ZGC trade-offs, heap sizing (-Xms/-Xmx), GC log analysis, and diagnosing OOM errors (heap vs metaspace vs thread stack) — directly required by the JD and untouched in this interview.
- [ ] HikariCP connection pool sizing: understand maximumPoolSize, connectionTimeout, and how to calculate pool size for a given thread-concurrency and database connection budget — tie this back to the MahaRERA tuning claim so you can answer follow-up questions.

## Transcript

**[0] INTERVIEWER**

Thanks for joining today, Anjali — let's get straight into it. You mentioned resolving N+1 query issues on the MahaRERA platform, which was serving 34,000 daily users — walk me through a specific N+1 problem you encountered, how you diagnosed it, and exactly what you changed to fix it.

**[1] CANDIDATE**

I mean, by default, the audio should have been on. Yeah, I don't remember what exactly I did there, but it was a complicated problem.

**[2] INTERVIEWER**

Thanks for your time, Anjali, but I need candidates to recall and articulate specific technical decisions they've owned — good luck with your search.