5 months ago
Responsibilities
- Architect and build LLM-powered systems with retrieval workflows, context management, agent prompts, and structured output pipelines.
- Orchestrate AI workflows using frameworks such as LangChain, LlamaIndex, or similar tools.
- Drive prompt engineering and iteration to meet product quality and reliability goals.
- Measure usefulness, factual correctness, latency, and user-experience impact through real-world evaluation metrics.
- Collaborate with product, platform, and backend teams on seamless system integration.
- Develop reliable and scalable production deployments with strong performance, cost efficiency, and observability.
Requirements
- 6+ years of software engineering experience, including at least 1 year building AI in production.
- Bachelor’s degree in Computer Science or a related field; a master’s degree is a plus.
- Demonstrated experience using LLMs in production workflows or complex prototypes.
- Strong coding ability in Python or an equivalent language, with familiarity with backend frameworks and cloud services.
- Experience with API integrations, database systems, and scalable architectures.
- Experience with multimodal models or multi-agent system design.
- Familiarity with AI safety guardrails, hallucination mitigation, and structured output enforcement.
- Knowledge of vector databases, RAG architectures, and prompt lifecycle tooling.
- Experience building real LLM applications and integrating AI systems with product APIs and backend services.
Tech Stack
Categories
About Seven AI
Seven AI (7AI) builds an AI-driven security operations platform for enterprises, combining federated SIEM, agentic investigation, threat hunting, and automated response. Delivered as software for SOC teams, it reduces repetitive triage and incident response work and supports large-scale environments. Founded in 2024 by Lior Div and Yonatan Striem-Amit, the company is privately held and headquartered in Boston, Massachusetts.