This role requires a blend of deep AI engineering expertise and strong software engineering discipline. You will work with LLMs, orchestration frameworks (LangChain, LangGraph, MCP), retrieval pipelines, and evaluation harnesses to build copilots, automated decision engines, and large-scale migration frameworks.
You ll be responsible for ensuring these systems are trustworthy, measurable, and safe with clear evaluation gates, grounding, and hallucination detection before rollout.
Success in this role means moving beyond prototypes and delivering AI applications that engineers rely on daily: copilots that triage incidents, systems that recommend adaptive configurations, services that automate multi-repo code migrations, and evaluators that keep models accountable. You will collaborate closely with SRE, Security, and various Infrastructure Foundations teams.
What You ll Do:
-
Build and ship LLM-powered systems that reduce toil, accelerate remediation, and improve decision-making in operations contexts.
-
Design and maintain evaluation frameworks: hallucination tests, regression harnesses, benchmarks, and quality gates for safe rollout.
-
Develop retrieval-augmented pipelines (RAG) and data strategies for grounding on logs, telemetry, runbooks, and system metadata.
-
Engineer AI copilots and natural-language interfaces to interact with operational data and workflows.
-
Create frameworks for large-scale automation such as safe code migration and transformation pipelines.
-
Apply adaptive AI techniques to optimize system configurations, predict anomalies, and recommend preventive actions.
-
Partner across teams collaborate with AI Platform (inference/serving), SRE/Infra/Data Service/DC (operational context), and Security (safe usage) while focusing your work on application logic, correctness, evaluation, and safety.
-
Implement guardrails and safety systems: prompt injection defenses, PII filtering, constrained decoding, and model observability.
-
Build developer-facing SDKs and APIs in Python/Go;intuitive UIs in JavaScript/React for human-in-the-loop workflows.
-
Leverage modern orchestration frameworks (LangChain, LangGraph, MCP, semantic routers) to coordinate multi-step, tool-augmented workflows.
What Youll Need:
-
10+ years of total experience in development with strong programming skills in JS, Python or Go.
Proven experience shipping LLM-based systems into production with measurable impact.
-
Expertise in evaluation and testing of LLMs (benchmarks, hallucination/regression tests, grounding metrics).
-
Hands-on experience with LLM orchestration frameworks: LangChain, LangGraph, MCP, agent frameworks, or equivalent.
-
Deep understanding of RAG pipelines: embeddings, retrieval quality metrics, re-ranking, and grounding precision/recall.
-
Ability to translate ambiguous operational problems into AI-first solutions with clear KPIs.
Bonus:
-
Experience with fine-tuning/adapters (LoRA, QLoRA, continual learning) and safety tuning.
-
Exposure to inference optimization and serving, partnering with platform teams on latency, scaling, and resilience.
-
Experience building AI copilots/assistants for engineers.
-
Frontend development in JavaScript/React for lightweight human-in-the-loop tooling.
-
Knowledge of reinforcement learning, adaptive systems, or optimization methods
Benefits of Working at CrowdStrike:
-
Remote-friendly and flexible work culture
-
Market leader in compensation and equity awards
-
Comprehensive physical and mental wellness programs
-
Competitive vacation and holidays for recharge
-
Paid parental and adoption leaves
-
Professional development opportunities for all employees regardless of level or role
-
Employee Networks, geographic neighborhood groups, and volunteer opportunities to build connections
-
Vibrant office culture with world class amenities
-
Great Place to Work Certified across the globe