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

I am a Software Engineer with deep experience building scalable, production-grade AI infrastructure at Meta and Google. I specialize in developing end-to-end systems for model serving, real-time inference, and developer-facing ML tools. I am proficient in Python, TypeScript, Go, and modern ML frameworks like PyTorch, TensorFlow, JAX, and Flax. I am skilled in architecting FastAPI-based microservices, GPU-accelerated model deployment pipelines, and React dashboards for LLM interaction, monitoring, and telemetry. I am adept at working across the full stack — from Kubernetes orchestration and Redis-backed caching to prompt evaluation frameworks and token-level frontend rendering. I am passionate about building reliable, observable, and performant AI platforms integrated directly into cloud-native infrastructure.…I am a Software Engineer with deep experience building scalable, production-grade AI infrastructure at Meta and Google. I specialize in developing end-to-end systems for model serving, real-time inference, and developer-facing ML tools. I am proficient in Python, TypeScript, Go, and modern ML frameworks like PyTorch, TensorFlow, JAX, and Flax. I am skilled in architecting FastAPI-based microservices, GPU-accelerated model deployment pipelines, and React dashboards for LLM interaction, monitoring, and telemetry. I am adept at working across the full stack — from Kubernetes orchestration and Redis-backed caching to prompt evaluation frameworks and token-level frontend rendering. I am passionate about building reliable, observable, and performant AI platforms integrated directly into cloud-native infrastructure.

Christopher Walsh

Developer, AI Engineer, Full Stack Developer, +2





I am a Software Engineer with deep experience building scalable, production-grade AI infrastructure at Meta and Google. I specialize in developing end-to-end systems for model serving, real-time inference, and developer-facing ML tools. I am proficient in Python, TypeScript, Go, and modern ML frameworks like PyTorch, TensorFlow, JAX, and Flax. I am skilled in architecting FastAPI-based microservices, GPU-accelerated model deployment pipelines, and React dashboards for LLM interaction, monitoring, and telemetry. I am adept at working across the full stack — from Kubernetes orchestration and Redis-backed caching to prompt evaluation frameworks and token-level frontend rendering. I am passionate about building reliable, observable, and performant AI platforms integrated directly into cloud-native infrastructure.…I am a Software Engineer with deep experience building scalable, production-grade AI infrastructure at Meta and Google. I specialize in developing end-to-end systems for model serving, real-time inference, and developer-facing ML tools. I am proficient in Python, TypeScript, Go, and modern ML frameworks like PyTorch, TensorFlow, JAX, and Flax. I am skilled in architecting FastAPI-based microservices, GPU-accelerated model deployment pipelines, and React dashboards for LLM interaction, monitoring, and telemetry. I am adept at working across the full stack — from Kubernetes orchestration and Redis-backed caching to prompt evaluation frameworks and token-level frontend rendering. I am passionate about building reliable, observable, and performant AI platforms integrated directly into cloud-native infrastructure.

Available to hire

I am a Software Engineer with deep experience building scalable, production-grade AI infrastructure at Meta and Google. I specialize in developing end-to-end systems for model serving, real-time inference, and developer-facing ML tools. I am proficient in Python, TypeScript, Go, and modern ML frameworks like PyTorch, TensorFlow, JAX, and Flax. I am skilled in architecting FastAPI-based microservices, GPU-accelerated model deployment pipelines, and React dashboards for LLM interaction, monitoring, and telemetry.

I am adept at working across the full stack — from Kubernetes orchestration and Redis-backed caching to prompt evaluation frameworks and token-level frontend rendering. I am passionate about building reliable, observable, and performant AI platforms integrated directly into cloud-native infrastructure.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Software Engineer at Meta

May 1, 2024 - Present

Contributed to the development of SentinelAI, an internal AI-driven incident response platform supporting Site Reliability Engineers and infrastructure teams during live outages. Built a Python and FastAPI backend with SSE streaming for modular prompt routing across internal services, and developed React and TypeScript frontend features including token-level large language model output rendering, interactive system actions, and telemetry visualizations with D3.js. Integrated Firebase Auth and TailwindCSS for secure, design-compliant access. Deployed GPU-based inference services using TorchScript and Triton on GKE clusters, optimized for low-latency startup. Implemented Redis-based context caching, Celery task workers for batch processing, and added observability instrumentation with OpenTelemetry and Prometheus for real-time metrics and tracing.

Software Engineer at Google

May 1, 2024 - August 5, 2025

Worked on the ML Infrastructure team supporting large-scale AI model deployment and inference optimization for Ads and Search. Developed distributed model serving pipelines using TensorFlow Serving, gRPC, and Envoy, deployed across multi-region Google Cloud Platform clusters with autoscaling and tracing. Built JAX/Flax-based training workflows optimized for TPU v4 pods and internal orchestration systems. Refactored data preprocessing pipelines with Apache Beam to reduce latency and enable real-time feature generation. Implemented feature caching layers with Redis and Bigtable, coordinated via Kafka and Pub/Sub. Built Go CLI tools for experiment management, React-based model monitoring dashboards, and an internal large language model prompt evaluation framework for performance comparison. Enhanced ML observability using OpenCensus integrated into logs and gRPC endpoints, partnered with SRE teams on fallback mechanisms, and participated in optimization sprints to reduce inference costs a

Software Engineer at Meta

May 1, 2024 - Present

At Meta, I contributed to the development of SentinelAI, an AI-driven incident response platform designed to support Site Reliability Engineers and infrastructure teams during live outages. I helped build the engineering console backend using Python and FastAPI, incorporating SSE streaming and modular prompt routing. I developed core features of the React and TypeScript interface, including token-level LLM output rendering and telemetry visualizations with D3.js. I integrated Firebase Auth for secure access and applied TailwindCSS to align with Meta's internal design guidelines. My work also involved deploying GPU-based inference services on GKE clusters using Helm and ArgoCD and optimizing latency. Additionally, I implemented Redis-based context caching, Celery task workers for batch log processing, and added observability instrumentation with OpenTelemetry and Prometheus for real-time metrics and tracing.

Software Engineer at Google

May 1, 2024 - August 5, 2025

While at Google, I worked on the ML Infrastructure team supporting large-scale AI model deployment and inference optimization for Ads and Search. I developed distributed model serving pipelines using TensorFlow Serving, gRPC, and Envoy, deployed across multi-region GCP clusters with autoscaling and request tracing. I built custom JAX/Flax-based training workflows optimized for TPU v4 pods, integrated into internal orchestration systems. I refactored data preprocessing jobs using Apache Beam, reducing latency by 45% and enabling real-time feature generation. My responsibilities included implementing feature caching with Cloud Memorystore and Bigtable, building Go-based CLI tools for model experiments, building React-based dashboards for real-time model monitoring, and designing an internal LLM prompt evaluation framework. I also contributed to ML observability stacks, partnered with SRE teams to improve inference reliability, and participated in quarterly optimization sprints focusing o