Senior AI Engineer
At a glance
Senior AI Engineering role at Seven AI. Boston · full-time · $165,000–$230,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Design LLM systems for security agents, covering retrieval, context handling, prompts and structured responses
- Connect AI workflows to product APIs and backend services using LangChain, LlamaIndex or comparable frameworks
- Refine prompts and context approaches to improve product quality and reliability
- Measure usefulness, factual accuracy, latency and user experience, then strengthen production performance, cost and observability
- Coordinate with product, platform and backend teams to bring integrations into production
What you bring
- At least six years in software engineering, including a year or more building production AI
- A computer science degree or a related bachelor's qualification
- You have launched LLM applications that became part of a product, rather than stopping at prototypes
- Strong Python or equivalent coding ability, with experience in APIs, backend integration, databases and cloud deployment
- Practical RAG and vector database experience, plus a workflow framework such as LangChain or another listed option
Who this fits
This role suits a senior engineer who builds and improves production LLM applications, with a focus on reliable product outcomes rather than training models from scratch. It is a Boston-based hybrid role.
From the employer
About 7AI
7AI is the foundational AI security company. Founded in 2024 by Cybereason co-founders Lior Div and Yonatan Striem-Amit, we came out of stealth in February 2025 to take on the non-human work of the SOC. Our platform pairs a federated SIEM with AI agents that detect, investigate, respond, and hunt, plus dedicated threat hunting and threat intelligence, with humans on the loop.
Backed by $166 million in total funding from investors including Index Ventures and Blackstone, we're building the AI foundation for security operations in the agentic era, and we're still early. That's the appeal: you'll join at a pivotal stage where your work shapes what 7AI becomes, alongside security veterans who've built this before. Our culture runs on respect, collaboration, and a shared bar for excellence, all pointed at one goal, delivering real outcomes for the customers who trust us to defend them.
Overview
Every AI agent's investigation is only as good as the LLM system underneath it. Get the retrieval, context, and prompting wrong, and the agent looks smart in a demo but falls apart on a real customer's data. As a Senior AI Engineer, you'll build the LLM-powered systems behind our security agents: retrieval workflows, context management, agent prompts, and structured output pipelines. This role is distinct from traditional ML engineering. Instead of training models from scratch, you'll compose, optimize, and scale AI systems that solve complex enterprise problems, working closely with product, platform, and backend teams to get them into production.
What You'll Do
Architect and build LLM-powered systems, including retrieval workflows, context management, agent prompts, and structured output pipelines.
Orchestrate AI workflows using LangChain, LlamaIndex, or similar frameworks, and integrate them with product APIs and backend services.
Own prompt engineering and iteration, refining prompts, templates, and context strategies to meet product quality and reliability goals.
Track real-world evaluation metrics such as usefulness, factual correctness, latency, and user experience impact, not just classic accuracy.
Work closely with product, platform, and backend teams to ensure integrations land cleanly.
Build reliable, scalable deployments that hold up on performance, cost efficiency, and observability in production.
What We're Looking For
6+ years of software engineering experience, including at least 1 year building AI in production.
BS in Computer Science or a related field.
Shipped LLM applications in production, not just prototypes, using large models in ways that meaningfully mattered to the product.
Strong coding skills in Python (or equivalent), with experience in API design, backend integration, database systems, and cloud deployment.
Hands-on experience with RAG, vector databases (Pinecone, Weaviate), and workflow frameworks like LangChain or Dust.
Comfortable architecting end-to-end solutions, including context windows, caching strategies, tool calls, and multi-step reasoning.
Experience with multi-modal models or multi-agent system design.
Familiar with AI safety guardrails, hallucination mitigation, and structured output enforcement.
Focused on product outcomes: the AI needs to work safely and reliably for users, not just perform well on paper.
Nice to Have
Master's degree in Computer Science or a related field.