A
Remote Fullstack AI Engineer - Cybersecurity & LLMs
Allen Recruitment
3 hours ago
Full-time
On-site
Sacramento, California, United States
If you’ve actually shipped LLM/agentic features into production (not just demos), this is a rare role where that experience is the main event.
We’re hiring a hands-on Fullstack Engineer to build “AI features” end-to-end inside a cybersecurity product: gather the right context from the platform, orchestrate LLM/agent calls reliably (auth, retries, rate limits, fallbacks), and turn outputs into clear, actionable workflows in the UI that real users trust.
This is a high-ownership, product-first environment. You’ll ship quickly, see how customers use (or don’t use) what you built, and iterate until it’s genuinely useful.
What you’ll own
End-to-end AI feature delivery: context → LLM/agent service → product workflow/UI Production-grade integrations: authentication/key handling, error states, retries, latency/perf tuning, safe degradation when AI services are down UI that makes AI usable: React/TypeScript components that turn “model output” into decisions, recommended actions, and automation suggestions Operability: monitoring/logging/metrics, usage analytics, and feedback loops so the AI improves over time What we’re prioritising
Hands-on LLM implementation in production (you’ve built it, shipped it, supported it) Agentic AI projects (tool/function calling, multi-step orchestration, real workflows; RAG a plus where relevant) Startup / product-company experience (pace, ambiguity, ownership) Strong product ownership mindset (you care about outcome, not just tickets) Bonus: security product exposure (SIEM/EDR/IAM, alerting/findings, investigations, compliance workflows) Tech stack
Core stack is Go + React/TypeScript (some Python in the mix) Go is a strong preference, but it’s not a hard requirement if you’re a strong engineer who can transition into Go quickly What matters most is proven “LLM/agentic shipping” + end-to-end ownership Logistics / constraints
Fully remote, but you must be based in the US or Europe (permanent hire via local entity/EOR) You need consistent overlap with core Central US hours Next Steps
Apply with your CV, and we’ll come back quickly to arrange a first conversation.
#J-18808-Ljbffr
End-to-end AI feature delivery: context → LLM/agent service → product workflow/UI Production-grade integrations: authentication/key handling, error states, retries, latency/perf tuning, safe degradation when AI services are down UI that makes AI usable: React/TypeScript components that turn “model output” into decisions, recommended actions, and automation suggestions Operability: monitoring/logging/metrics, usage analytics, and feedback loops so the AI improves over time What we’re prioritising
Hands-on LLM implementation in production (you’ve built it, shipped it, supported it) Agentic AI projects (tool/function calling, multi-step orchestration, real workflows; RAG a plus where relevant) Startup / product-company experience (pace, ambiguity, ownership) Strong product ownership mindset (you care about outcome, not just tickets) Bonus: security product exposure (SIEM/EDR/IAM, alerting/findings, investigations, compliance workflows) Tech stack
Core stack is Go + React/TypeScript (some Python in the mix) Go is a strong preference, but it’s not a hard requirement if you’re a strong engineer who can transition into Go quickly What matters most is proven “LLM/agentic shipping” + end-to-end ownership Logistics / constraints
Fully remote, but you must be based in the US or Europe (permanent hire via local entity/EOR) You need consistent overlap with core Central US hours Next Steps
Apply with your CV, and we’ll come back quickly to arrange a first conversation.
#J-18808-Ljbffr