Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m a software engineer focused on building scalable, production-grade AI infrastructure. I’ve shipped end-to-end systems for model serving, real-time inference, and developer-facing ML tools at Meta and Google, with hands-on experience across Python, TypeScript, Go, and modern ML frameworks. I enjoy designing cloud-native, observable platforms that blend GPU-accelerated deployment, robust data pipelines, and intuitive dashboards for SREs and data scientists. Driven by reliability and performance, I build tools and pipelines that scale with teams and data. My work spans Kubernetes-based orchestration, Redis-backed caching, and prompt evaluation frameworks, all aimed at delivering low-latency, traceable AI systems integrated into production infrastructure.…I’m a software engineer focused on building scalable, production-grade AI infrastructure. I’ve shipped end-to-end systems for model serving, real-time inference, and developer-facing ML tools at Meta and Google, with hands-on experience across Python, TypeScript, Go, and modern ML frameworks. I enjoy designing cloud-native, observable platforms that blend GPU-accelerated deployment, robust data pipelines, and intuitive dashboards for SREs and data scientists. Driven by reliability and performance, I build tools and pipelines that scale with teams and data. My work spans Kubernetes-based orchestration, Redis-backed caching, and prompt evaluation frameworks, all aimed at delivering low-latency, traceable AI systems integrated into production infrastructure.

Christopher Walsh

AI Engineer, Full Stack Developer, Back-End Developer, +7





I’m a software engineer focused on building scalable, production-grade AI infrastructure. I’ve shipped end-to-end systems for model serving, real-time inference, and developer-facing ML tools at Meta and Google, with hands-on experience across Python, TypeScript, Go, and modern ML frameworks. I enjoy designing cloud-native, observable platforms that blend GPU-accelerated deployment, robust data pipelines, and intuitive dashboards for SREs and data scientists. Driven by reliability and performance, I build tools and pipelines that scale with teams and data. My work spans Kubernetes-based orchestration, Redis-backed caching, and prompt evaluation frameworks, all aimed at delivering low-latency, traceable AI systems integrated into production infrastructure.…I’m a software engineer focused on building scalable, production-grade AI infrastructure. I’ve shipped end-to-end systems for model serving, real-time inference, and developer-facing ML tools at Meta and Google, with hands-on experience across Python, TypeScript, Go, and modern ML frameworks. I enjoy designing cloud-native, observable platforms that blend GPU-accelerated deployment, robust data pipelines, and intuitive dashboards for SREs and data scientists. Driven by reliability and performance, I build tools and pipelines that scale with teams and data. My work spans Kubernetes-based orchestration, Redis-backed caching, and prompt evaluation frameworks, all aimed at delivering low-latency, traceable AI systems integrated into production infrastructure.

Available to hire

I’m a software engineer focused on building scalable, production-grade AI infrastructure. I’ve shipped end-to-end systems for model serving, real-time inference, and developer-facing ML tools at Meta and Google, with hands-on experience across Python, TypeScript, Go, and modern ML frameworks. I enjoy designing cloud-native, observable platforms that blend GPU-accelerated deployment, robust data pipelines, and intuitive dashboards for SREs and data scientists.

Driven by reliability and performance, I build tools and pipelines that scale with teams and data. My work spans Kubernetes-based orchestration, Redis-backed caching, and prompt evaluation frameworks, all aimed at delivering low-latency, traceable AI systems integrated into production infrastructure.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

Aragonese

Advanced

Bashkir

Advanced

Work Experience

Software Engineer at Meta

May 1, 2024 - Present

SentinelAI is an AI-driven incident response platform built to support Site Reliability Engineers during live outages. I contributed to the SentinelAI engineering console using Python + FastAPI with SSE streaming and modular prompt routing across internal services (log systems, service graphs, and incident archives). I built core features of the React + TypeScript interface, including token-level LLM output rendering, interactive system actions, and telemetry visualizations with D3.js. I integrated Firebase Auth for secure team-specific access, and applied TailwindCSS to align with internal design guidelines. I helped implement and deploy GPU-based inference services (TorchScript + Triton) on internal GKE clusters, optimized for low-latency startup. I also developed Redis-based context caching and contributed to Celery workers for background processing of batch log summaries and incident timelines, with observability instrumentation via OpenTelemetry, Prometheus, and internal monitorin

Software Engineer at Google

November 1, 2022 - May 1, 2024

Supported ML infrastructure for Ads and Search; built scalable backend systems for training and serving multimodal models; developed distributed model serving pipelines with TensorFlow Serving, gRPC, and Envoy across multi-region GCP clusters with autoscaling and request tracing. Created JAX/Flax-based training workflows for ad ranking on TPU v4 pods with integration into internal orchestration (Borg + Blaze). Refactored data preprocessing with Apache Beam (Python), enabling real-time feature generation from streaming logs. Implemented feature caching layers with Cloud Memorystore (Redis) and Bigtable, coordinated via Kafka and Pub/Sub topics. Created Go-based CLI tools for launching experiments, tracking rollout metrics, and managing evaluation datasets across teams. Built real-time model monitoring dashboards in React + TypeScript to visualize output drift, latency, and top-K error distributions. Designed internal LLM prompt evaluation framework for comparing model completions across