I’m a software engineer who builds cloud-native, distributed systems and AI-powered applications, with a strong focus on production reliability. I’ve worked across Java/Spring microservices, REST/gRPC APIs, event-driven architectures, and AWS-based data pipelines—designing systems that handle real workload and recover gracefully from failures.
I also enjoy developing end-to-end AI features like RAG pipelines and ML inference workflows, including retrieval and evaluation, orchestration with Kafka/workers, and performance tuning. From API governance to containerized deployments on Kubernetes, I bring a practical, developer-friendly approach to shipping maintainable services and delivering measurable improvements.
Skills
Experience Level
Language
Work Experience
Education
Qualifications
Industry Experience
- Built a self-healing API gateway for agentic workflows and LLM-powered applications using Python and FastAPI for reliable AI-driven user interactions despite upstream failures.
- Architected a semantic caching layer utilizing Redis and local embedding models to intercept high-similarity queries, bypassing costly LLM inference entirely and heavily reducing p99 response latency.
- Orchestrated LLM infrastructure to support continuous AI-driven interactions, specifically engineering fallbacks to handle edge cases like rate-limiting and external API downtime.
- Engineered and orchestrated LLM infrastructure, including fallbacks for AI-driven interaction edge cases like rate-limiting and API downtime.
- Instrumented the gateway with rigorous Prometheus and Grafana telemetry to monitor cache hit rates and
system degradation, deploying data quality gates to reject prompt injection anomalies automatically.
Hire a Full Stack Developer
We have the best full stack developer experts on Twine. Hire a full stack developer in Amherst today.