Senior Software Engineer | Research Infrastructure & AI Systems | Leamington Spa, UK
Building resilient, production-grade systems that bridge infrastructure engineering with cutting-edge AI research.
Senior Software Engineer with 4+ years of production experience designing scalable infrastructure, data pipelines, and AI-orchestrated systems. Specialized in research software engineering, multi-provider LLM systems, and production reliability.
Key Impact:
- Architected enterprise infrastructure supporting 200+ repositories and 50+ teams
- Resolved 132 production incidents in one year with ~1 hour MTTR
- Reduced deployment lead time by 35% through CI/CD automation
- Achieved 99%+ uptime on critical multi-provider LLM orchestration systems
| Area | Technologies & Specializations |
|---|---|
| Languages & Frameworks | Python 3.11+ • FastAPI • C# • TypeScript • SQL |
| AI & LLM Systems | Multi-provider LLM orchestration • Gemini API • Groq • Agno framework • RAG • Fine-tuning |
| Cloud & Infrastructure | AWS (EC2, Lambda, S3) • Azure (AKS, Functions, Monitor) • Kubernetes • Terraform • GitHub Actions |
| Data Engineering | Databricks (PySpark) • Snowflake • PostgreSQL • Real-time ingestion • Anomaly detection |
| DevOps & Reliability | CI/CD automation • Infrastructure-as-Code • Monitoring (Prometheus/Grafana) • Incident response |
| Software Design | SOLID Principles • Design Patterns (Facade, Component Isolation) • System architecture • Testing |
Production research pipeline ingesting 200+ RSS feeds with multi-provider LLM orchestration and intelligent temporal windowing.
Key Features:
- Resilience: Gemini primary + Groq fallback with 3-retry exponential backoff → 99%+ uptime
- Data Integrity: Strict error handling ensuring visible failures for research reproducibility
- Temporal Intelligence: Dynamic gap calculation (T-1 to T-118 days) for catch-up scenarios
- Quality: 5 unit tests • ~75% code coverage • Comprehensive production documentation
- Automation: GitHub Actions CI/CD with scheduled daily execution and manual triggers
Repository: github.com/SushP07/ai-news-synthesizer
| Metric | Value |
|---|---|
| Years of Production Experience | 4+ years |
| Teams Supported | 50+ engineering teams |
| Infrastructure Scale | 200+ repositories |
| Production Incidents Resolved | 132 (past year) |
| Mean Time to Resolve | ~1 hour |
| CI/CD Lead Time Reduction | 35% |
| System Uptime (Critical Systems) | 99%+ |
| Code Coverage (Research Projects) | ~75% |
| Automated Data Validation | 91% |
MSc Applied Artificial Intelligence | Cranfield University (2021-2022)
- Surpassed state-of-the-art benchmarks on FOD-A dataset using BYOL
BSc Computer Science | Rashtrasant Tukdoji Maharaj Nagpur University (2017-2021)
AWS Certified AI Practitioner (2023)
Databricks Generative AI Fundamentals (2024)
- Portfolio: sushp07.github.io
- DagsHub ML Workspace: dagshub.com/SushP07