> Markdown version of [/jobs/ext/4785191-full-stack-ai-engineer-bay-area-ca-onsite](https://www.wearedevelopers.com/jobs/ext/4785191-full-stack-ai-engineer-bay-area-ca-onsite). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Full Stack & AI Engineer @ Bay Area, CA (Onsite) - **Company:** HAXANT TECHNOLOGIES LLC - **Location:** San Francisco, CA, United States - **Experience:** Expert - **Contract:** Contract - **Skills:** LangGraph Framework, Artificial Intelligence, Amazon Web Services, Computing Platforms, Artificial Neural Networks, Automation of Tests, Microsoft Azure, C++ (Programming Language), Cloud Computing, Cloud Engineering, Code Coverage, Communications Protocols, Databases, Extract Transform Load (ETL), Data Security, Cursor, Database Queries, DevOps, Programming Tools, Python (Programming Language), PostgreSQL, Machine Learning, Node.Js, E2e Testing, Next.js, TypeScript, Pinecone, Pulumi, Google Cloud, High Performance Computing, Tailwind, Pytorch, Surrogate Models, ReactJS, Large Language Models, Claude Code, Multi-Agent Systems, State Machines, Generative AI, Amazon Virtual Private Cloud (VPC), Backend, Agentic-AI, Fastapi, Kubernetes, Information Technology, Deployment Automation, CrewAI, AutoGen, Build Tools, Milvus, Graphql, Front End Software Development, Vertica, Model Context Protocol, Model Inference, Terraform, Docker, Microservices - **Published:** November 19, 2026 - **Apply:** https://www.dice.com/job-detail/fe0d6a24-b116-49d9-b017-0825bf4f6415 ## About the Role · Full-Stack Competence: 5+ years of production experience with modern backend and frontend stacks (Python/FastAPI, TypeScript/React/Next.js, Node.js, Tailwind, GraphQL/REST). · Agentic & LLM Expertise: Hands-on experience integrating LLM APIs and building/deploying production-grade agentic frameworks (LangGraph, AutoGen, CrewAI, or bespoke state machines), advanced tool-calling, retrieval-augmented generation (RAG) pipelines, and evaluation frameworks in production software. · Data & Systems Infrastructure: Deep experience designing schemas and managing relational, time-series, and vector databases (PostgreSQL, TimescaleDB, ClickHouse, Pinecone/Milvus). · Cloud & DevOps Expertise: Deep hands-on experience provisioning cloud infrastructure (AWS/Google Cloud Platform/Azure), building CI/CD pipelines, writing Infrastructure as Code (Terraform), and managing Kubernetes/Docker clusters. · AI-First Developer Leverage: Daily fluency with agentic coding environments (especially Claude Code, Cursor, or custom terminal agents) and protocols like MCP to accelerate prototyping, multi-file refactors, and test coverage. · Startup Velocity & Customer Focus: Ability to navigate ambiguity, ship working code daily, iterate directly based on customer feedback, and take extreme end-to-end ownership. · Export Control Compliance: Due to U.S. export control regulations (EAR/ITAR), candidates must be a "U.S. Person" as defined under 22 CFR § 120.62 / 15 CFR § 772.1 (U.S. Citizen, U.S. National, Lawful Permanent Resident / , or granted Asylee/Refugee status). Bonus Points · Advanced Degree: Ph.D. from a Tier-1 university in Computer Science, Applied Physics, Materials Science, Chemical Engineering, Electrical Engineering, or related technical disciplines. · Scientific & Applied ML Background: Proven experience building and deploying scientific ML models, PINNs, surrogate models, or complex physical simulation workflows (fluids, plasma, materials, or chemical engineering domains). · Core Compute/Systems: Experience with high-performance computing and physics engines (C++). · AI & Physics Modeling: Familiarity with physics-informed machine learning and AI frameworks (NVIDIA Modulus, NVIDIA NeMo, PyTorch). · Semiconductor Domain Knowledge: Prior background or academic research in semiconductor processing, nanotechnology, thin films (ALD, CVD, Etch, CMP), or electronic materials. · Fab Protocols & Tool Interfacing: Experience interfacing with hardware control systems, industrial IoT, or fab communication protocols (SECS/GEM, EDA/Interface A). · Tooling & Protocol Extensions: Experience authoring custom MCP servers or building integrations for agentic coding tools. · Early-Stage Experience: Previous experience as a founder, founding engineer, or early-stage engineer in a venture-backed deep-tech or enterprise AI startup. ## Description We are seeking an exceptional Full-Stack & AI Engineer who thrives at the intersection of rapid production engineering, scalable software architecture, and autonomous agentic systems. We operate with extreme engineering leverage: our team heavily uses agentic developer tooling, including Claude Code, Cursor, and the Model Context Protocol (MCP), to ship robust, production-grade systems at 10x startup velocity. You will be the architectural bedrock of our product, building the end-to-end software platform and cloud infrastructure that bridges our physical process models and large-scale autonomous LLM agents, and deploying directly into customer evaluations and pilots. Key Responsibilities 1. Full-Stack Engineering & Platform Architecture · Architect, build, and maintain our end-to-end software platform from scratch: high-performance backend microservices (Python/FastAPI/AsyncIO), complex database layers, and intuitive engineering dashboards (TypeScript/React/Next.js). · Design and construct robust ETL pipelines and secure data connectors capable of ingesting high-frequency equipment time-series telemetry (OES, RGA) and legacy SECS/GEM or flat-file fab logs. 2. Cloud Infrastructure, Deployment & Continuous Testing (DevOps) · Design, provision, and manage scalable cloud infrastructure across AWS, Google Cloud Platform, or Azure using Infrastructure as Code (Terraform, Pulumi). · Build and maintain rigorous CI/CD pipelines with comprehensive continuous testing (automated unit, integration, and end-to-end testing) to ensure seamless, zero-downtime deployments and highly reliable iteration cycles. · Orchestrate and scale containerized workloads using Docker and Kubernetes, optimizing compute resources for heavy ML, physics simulations, and LLM inference tasks. 3. Agentic AI & Autonomous Scientific Workflows · Develop robust, deterministic multi-agent systems that autonomously decompose complex engineering goals into actionable experimental design, data querying, and simulation workflows. · Build tool-use capabilities and MCP (Model Context Protocol) servers allowing agents to execute scientific code, run numerical solvers, and synthesize technical papers/patents. · Implement structured reasoning, guardrails, state-machine verifiers, and memory stores to ensure agent outputs meet rigorous physical plausibility and safety criteria 4. AI-Augmented Velocity & Agentic Tooling · Leverage agentic coding tools (such as Claude Code CLI and Cursor) to autonomously generate test coverage, refactor codebases, automate deployment tasks, and maximize raw development output. · Collaborate closely with the AI and Physics teams to seamlessly integrate LLM agents, LangGraph workflows, and Physics-Informed Neural Networks (PINNs) into the production backend. 5. Customer Delivery & Pilot Execution · Own technical deployment and integration during pilot programs with equipment OEMs and cleanroom customer sites. · Work shoulder-to-shoulder with customer process engineers, CTOs, and fab managers to translate complex domain challenges into working product capabilities. · Deploy air-gapped or hybrid on-prem/VPC customer instances ensuring enterprise-grade data isolation, encryption, and zero-data-leakage compliance. 6. Physics AI & Scientific Machine Learning (Bonus requirement) · Design and implement Physics-Informed Neural Networks (PINNs), neural operators (FNOs, DeepONets), and surrogate models to simulate plasma dynamics, chemical kinetics, thermal budgets, and material interfaces. · Build active learning and Bayesian optimization pipelines to recommend optimal recipe parameters (gas flow, RF power, pressure, temperature profiles) under sparse, high-cost experimental constraints. · Ingest and featurize complex, multimodal semiconductor fab telemetry: optical emission spectroscopy (OES), residual gas analysis (RGA), in-situ metrology, and wafer-level morphology data.