Senior AI Engineer
Confirmed on the employer's own hiring board on Sep 28, 2026. First seen by Alion on Jul 17, 2026.
Senior AI Engineer
Tel Aviv, Israel · Full-time
About Pi
We are Pi Security, founded by veterans from Tesla and Microsoft, redefining Application Security through autonomous AI agents and modern orchestration. Our platform connects to our customers codebases and engineering tools, and deploys AI agents that autonomously find, prioritize, and remediate security issues - from code-level vulnerabilities to architectural design gaps.
About The Position
We are looking for a high-ambition engineer to join our team in Israel and own the
intelligence layer of our platform: the agents that analyze customer codebases, reason about
vulnerabilities, and produce remediations autonomously.
First and foremost, this is a senior software engineering role. You will design and build production services, write code across the stack, and own what you ship end to end - the AI agents are software, and you build the systems they run on. This is not a prompt-tweaking role: you will design multi-step agentic systems end to end - context engineering, tool design, orchestration, evaluation, and production monitoring - on a "zero legacy" stack (Python, Temporal, K8s, and frontier LLMs). We value a low-ego mindset and a passion for solving deep technical challenges in a fast-paced, collaborative environment.
Responsibilities
Backend Development: Design and build high-performance production services using Python, FastAPI, and asynchronous workers - the foundation your agents run on.
Agent Development: Design and build autonomous, multi-step AI agents for security analysis, code review, and threat modeling - including tool use, structured outputs, and long-running agentic loops.
Context Engineering: Build the retrieval and grounding layer that feeds agents the right code, docs, and organizational knowledge at the right time.
Evaluation & Quality: Own the eval pipeline - build benchmarks, measure agent output quality, catch regressions, and drive systematic prompt and model iteration.
Orchestration: Run agents as durable Temporal workflows that survive failures, scale across tenants, and stay observable in production.
LLM Operations: Manage prompt versioning, tracing, token economics, model selection, and fallback strategies across providers.
Engineering Culture: Lead architectural discussions, participate in deep-dive code reviews, and drive incident response.
Requirements
At least 4 years of experience in software development, designing, building, and operating production backend services.
Python Expertise: Strong professional background with a focus on modern, asynchronous Python.
Agentic AI Experience: Proven experience building LLM-powered agents in production - tool calling, multi-step reasoning, structured outputs - not just API wrappers or chatbots.
Evaluation Mindset: You treat prompts and agents as systems to be measured, not vibes to be tuned. Experience with eval frameworks, tracing, or LLM observability.
System Design: You can reason about latency, cost, reliability, and failure modes of LLM-based systems at scale.
Problem Solver: A fast learner with outstanding problem-solving skills who thrives in a "zero legacy" environment.
Team Player: A collaborative engineer with a focus on collective success and technical excellence.
Nice-to-Have
Experience with Temporal or similar distributed workflow engines.
Experience with static analysis, program comprehension, or codebase-scale retrieval.
Background in cybersecurity or application security products.