AI Engineer

We’re Looking for a Generative AI Engineer to Join a Leading Defense Company!

📍 Haifa, Israel

Job Description:

Join an AI Infrastructure team focused on integrating, deploying, and extracting real business value from existing Large Language Models (LLMs)

.End‑to‑end development of LLM‑based systems, with a strong emphasis on hands‑on design and implementation of Agents, from initial concept through production

.Design and implement agent logic, including task decomposition, context management, decision‑making, interaction with external tools, and a deep understanding of LLM capabilities and limitations

.Develop the Agent client that communicates with the LLM (not just usage of off‑the‑shelf libraries), including orchestration, data flow control, and state management

.Full ownership of LLM‑related services: APIs, data pipelines, and integration with existing systems

.Build, deploy, and optimize RAG (Retrieval‑Augmented Generation) pipelines, including document ingestion, chunking, embeddings, vector indexing, retrieval, re‑ranking, and caching

.Work with MCP (Model Context Protocol): standardizing tools and contexts, defining security and access boundaries, and exposing model capabilities safely

.Advanced prompt management: versioning, guardrails, safety filters, and architectures that support rapid experimentation and iteration

.Integration and orchestration using LangChain and LiteLLM, including multi‑provider model abstraction, fallbacks, caching, and cost/performance optimization

.Dynamic work in an R&D environment, requiring fast context switching between tasks, PoCs, and delivery to production

.Close collaboration with Product, Data, and DevOps teams; writing clean, maintainable code; automated testing; CI/CD; and clear documentation

.

Requiremen

ts:
3–6 years of software engineering experience, including 1–3 years of hands‑on experience building AI / LLM‑based syst

ems.No requirement for Data Scientist experience or model training; strong experience using existing models and a solid conceptual understanding of LLM capabilities and constraints is essent

ial.Proven experience designing and leading complex agents end‑to‑end, including agent logic, orchestration, and LLM clie

nts.Strong proficiency in Python and C/C++, with emphasis on performance, reliability, and test

ing.Hands‑on experience with vector databases (Pinecone / Weaviate / FAISS / Elasticsearch), embeddings, retrievers, and re‑rank

ers.Experience deploying RAG or agentic systems to production environme

nts.System‑level observability mindset: logs, metrics, traces, and dashboa

rds.Strong fundamentals in security: authentication, authorization, token management, and rate limit

ing.High sense of ownership, strong self‑learning skills, ability to work independently in a loosely defined environment, and excellent cross‑team communicat

ion.Experience working on existing systems at scale, with the ability to quickly onboard to legacy codebases and continuously improve the platf

orm.Mental flexibility and the ability to switch quickly between ta