Generative AI Engineer

We’re Hiring: AI Developer

Join a fast-growing cybersecurity company developing a cutting-edge AI platform that enables organizations to build agents and AI applications on the same platform.

Location: [Flexible / specify if needed]

Experience Level: Mid-Senior

Key Responsibilities

• Design, develop, and lead AI features for the product and agent builder – from architecture and prototyping to production and monitoring.
• Develop agent orchestration (tool/function calling, memory, workflows), establish RAG pipelines, and build fast inference services.
• Select and integrate LLMs and embeddings (OpenAI, Anthropic, open-source), including prompt design, guardrails, and fine-tuning.
• Build secure integrations and SDKs for external systems (REST/GraphQL APIs, webhooks, OAuth).
• Implement evaluation and observability processes to ensure quality, accuracy, and cost efficiency at scale.
• Work cross-functionally to translate user needs into solutions, mentor teammates, and implement best practices.
• Lead testing, CI/CD, performance, reliability, security, and cost optimization initiatives.

Requirements

Must-have

• 5+ years of software development experience, including 3+ years with ML/AI or LLM systems in production.
• Proficient in Python and experience with TypeScript/Node.js (or similar), with production release experience.
• Hands-on experience with LLMs: prompt design, tool/function calling, RAG, agent frameworks (LangChain, LlamaIndex, Semantic Kernel) or custom orchestration.
• Experience with vector databases (pgvector, Pinecone, Weaviate), search engines (Elasticsearch/OpenSearch), SQL (Postgres), and Redis.
• Cloud experience (AWS/GCP/Azure), Docker, Kubernetes/Lambda, CI/CD, and monitoring.
• Skilled in API design and distributed systems with focus on performance, reliability, security, and cost efficiency.
• Product-oriented thinking, excellent communication, and end-to-end ownership in a dynamic environment.
• Degree in Computer Science/Engineering or equivalent experience.

Nice-to-have

• Experience building no-code/low-code platforms or workflow engines.
• Experience in fine-tuning/LoRA, distillation, embeddings, and GPU inference optimization (vLLM, TensorRT/Triton).
• Experience in LLM evaluation and observability (Langfuse, Weights & Biases), A/B testing, prompt/version management.
• Contributions to open-source, publications, or experience launching AI/agentic systems in production.

Why Join Us?

• Be part of a high-growth cybersecurity company shaping the next generation of AI platforms.
• Work on state-of-the-art AI technologies, agent orchestration, and LLM production.
• Collaborate with a talented, cross-functional team in a dynamic, fast-moving environment.