Full Stack AI Engineer

Haxant Technologies

San Francisco, CA • 11m ago • On-site

Senior

On-site

80 - 85 USD/yr

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Potential salary for Full Stack AI Engineer role

Improve your resume now

$80 – $85/year

Quick Facts

  • Role: Full Stack AI Engineer
  • Focus: End-to-end platform engineering + agentic AI systems
  • Work: Backend/Full-Stack development, data pipelines, cloud/DevOps, and customer pilot deployments (including air-gapped/hybrid environments)

Description

You will build an end-to-end software platform that bridges physical process models with large-scale autonomous LLM agents, and deploy it directly into customer evaluations and pilots. The role combines production backend microservices and dashboards, secure ETL/data connectors for equipment telemetry and legacy fab logs, robust CI/CD and cloud infrastructure, and deterministic multi-agent scientific workflows with safety/guardrails. You will also own technical deployment and integration during pilots with OEMs and cleanroom customer sites.

Responsibilities

  • Architect and build production-grade backend microservices, database layers, and engineering dashboards
  • Design ETL pipelines and secure data connectors for high-frequency equipment time-series telemetry and legacy SECS/GEM or flat-file fab logs
  • Provision and manage scalable cloud infrastructure using Infrastructure as Code
  • Implement CI/CD pipelines with comprehensive continuous testing and zero-downtime deployments
  • Orchestrate and scale containerized workloads (ML, physics simulations, LLM inference) with Docker and Kubernetes
  • Develop deterministic multi-agent systems for decomposing goals into experimental design, data querying, and simulation workflows
  • Build tool-use capabilities via MCP servers and enable agents to run scientific code and numerical solvers
  • Add structured reasoning, guardrails, state-machine verifiers, and memory stores for physical plausibility and safety
  • Integrate LLM agents and LangGraph workflows with Physics-Informed Neural Networks (PINNs) in the production backend
  • Own pilot deployments with equipment OEMs and customer sites, including air-gapped or hybrid on-prem/VPC setups with encryption and zero-data-leakage compliance
  • Use agentic coding tools to accelerate refactors, testing, and deployment tasks

Requirements

  • 5+ years of production full-stack experience (Python/FastAPI; TypeScript/React/Next.js; Node.js; Tailwind; GraphQL/REST)
  • Hands-on experience integrating LLM APIs and deploying production-grade agentic frameworks (LangGraph, AutoGen, CrewAI, or bespoke state machines)
  • Advanced RAG/tool-calling and production evaluation frameworks
  • Deep experience with relational, time-series, and vector databases (PostgreSQL, TimescaleDB, ClickHouse, Pinecone/Milvus)
  • Deep hands-on cloud/DevOps experience provisioning AWS/GCP/Azure, building CI/CD, and using Terraform
  • Experience managing Kubernetes/Docker clusters
  • Daily fluency with agentic coding environments (Claude Code, Cursor, or custom terminal agents) and MCP
  • Ability to operate in ambiguity and ship working code daily with end-to-end ownership
  • U.S. Person eligibility for EAR/ITAR export control compliance

Benefits

Not specified in the provided posting.

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report