- Страна
- Грузия
Откликайтесь
на вакансии с ИИ

Senior Software Engineer, AI Core
Высокий балл обусловлен работой над передовыми технологиями (AI Agents) в престижной компании Chainalysis, удаленным форматом работы и использованием современного стека (Effect, TypeScript). Роль предполагает высокую степень ответственности и влияние на продукт.
Сложность вакансии
Роль требует глубоких знаний в области LLM (агенты, оркестрация, RAG) и серьезного опыта в системном дизайне, включая безопасность и изоляцию арендаторов (tenant isolation). Использование стека Effect и TypeScript на продвинутом уровне добавляет сложности.
Анализ зарплаты
В объявлении не указана зарплата, но для позиции Senior AI Engineer в международной компании с удаленным форматом работы в регионе Грузии, рыночные предложения обычно значительно выше локальных средних показателей. Указанный диапазон отражает глобальные стандарты для опытных инженеров в сфере блокчейна и ИИ.
Сопроводительное письмо
I am writing to express my strong interest in the Senior Software Engineer, AI Core position at Chainalysis. With a robust background in full-stack development and a deep focus on LLM orchestration, I am particularly drawn to your mission of building a secure, sandboxed execution environment for AI agents. My experience in developing production-grade AI features, including prompt engineering and RAG systems, aligns perfectly with your team's goal of grounding AI reasoning in proprietary blockchain data.
In my previous roles, I have consistently demonstrated high ownership of the full development lifecycle, from designing complex backend architectures in typed languages to shipping intuitive frontend interfaces. I am especially excited about your use of the Effect ecosystem and TypeScript, as I am a strong advocate for functional programming patterns to manage concurrency and state in distributed systems. I am eager to bring my expertise in tenant isolation and secure execution to help Chainalysis deliver reliable, AI-driven automation to your global customer base.
Составьте идеальное письмо к вакансии с ИИ-агентом

Откликнитесь в chainalysis-careers уже сейчас
Присоединяйтесь к лидерам блокчейн-аналитики и создавайте будущее ИИ-агентов в Chainalysis уже сегодня!
Описание вакансии
The AI Core team builds the platform that gives users AI-driven access to Chainalysis's blockchain investigation and compliance products. We build the agent runtime, the execution infrastructure, and the tool and skill systems that let AI reason about what users need and deliver answers, artifacts, and automation grounded in Chainalysis's proprietary data across sandboxed environments, durable workflows, and a deep catalog of product integrations. We run a small team with high ownership; we're looking for engineers who care about building systems where AI has real tools, real data, and real consequences.
In this role, you’ll:
- Design and build the agent platform end to end, from the context and tool layer that shapes what agents can reason about, through the execution runtime where code runs, to the interfaces that expose results to users.
- Own the skill architecture, designing how agents discover, learn about, and invoke capabilities across Chainalysis's product suite. This includes writing skill client libraries, their documentation, and testing them end to end.
- Build and operate sandboxed execution environments where agent-generated code runs with tenant-level security boundaries and durable file persistence.
- Ship full-stack features across frontend, backend, skill libraries, and infrastructure. You own the full lifecycle from design through production operation.
- Develop the workflow platform that lets users automate complex processes beyond single conversations.
- Drive AI quality, cost, and observability, including multi-model orchestration, context window management, prompt engineering, and tracing across multi-step agent runs.
We’re looking for candidates who have:
- Built and shipped full-stack features across frontend, backend, and infrastructure, with demonstrated ownership from design through production operation.
- Worked with LLMs in production and formed real opinions from it. Tool use, agent orchestration, streaming, prompt engineering, or retrieval-augmented generation. You've hit the failure modes and learned from them.
- A working understanding of how to structure what an agent knows and can do within the constraints of a context window. You've thought about the tradeoffs between baking knowledge into prompts, exposing tools, and letting agents write code against documented APIs.
- Deep backend engineering fundamentals in a typed language: concurrency, error handling, state management, and system design.
- Built or operated systems with real security constraints, tenant isolation, scoped credentials, sandboxed execution, or similar patterns where trust boundaries matter.
You might also have:
- Designed tool interfaces or capability systems for AI agents, skills, function schemas, or similar patterns for giving models structured access to external systems
- Worked with the Effect ecosystem or strongly-typed functional programming in TypeScript
- Built multi-tenant platforms or systems with enterprise security requirements
- Experience in Python library development or designing SDKs for programmatic consumption
- Worked within Blockchain, FinTech or B2B SaaS companies
Technologies we use:
- TypeScript, Effect, Node.js
- React, TanStack Router, TanStack Query, Tailwind, shadcn
- Various AI Frameworks (Vercel AI SDK, Agent SDK, OpenCode)
- Python
- PostgreSQL
- AWS Lambda, S3, STS, CloudWatch, ECR
- OpenTelemetry
- Docker, pnpm, Turborepo, Vitest
- Amazon Bedrock, Google Vertex AI
About Chainalysis
Blockchain technology is powering a growing wave of innovation. Businesses and governments around the world are using blockchains to make banking more efficient, connect with their customers, and investigate criminal cases. As adoption of blockchain technology grows, more and more organizations seek access to all this ecosystem has to offer. That’s where Chainalysis comes in. We provide complete knowledge of what’s happening on blockchains through our data, services, and solutions. With Chainalysis, organizations can navigate blockchains safely and with confidence.
You belong here.
At Chainalysis, we believe that diversity of experience and thought makes us stronger. With both customers and employees around the world, we are committed to ensuring our team reflects the unique communities around us. We’re ensuring we keep learning by committing to continually revisit and reevaluate our diversity culture.
We encourage applicants across any race, ethnicity, gender/gender expression, age, spirituality, ability, experience and more. If you need any accommodations to make our interview process more accessible to you due to a disability, don't hesitate to let us know. You can learn more here. We can’t wait to meet you.
Создайте идеальное резюме с помощью ИИ-агента

Навыки
- TypeScript
- Python
- LLM
- OpenTelemetry
- PostgreSQL
- RAG
- Prompt Engineering
- React
- Docker
- AWS Lambda
- Node.js
- Amazon S3
- Google Vertex AI
- Amazon ECR
- Amazon CloudWatch
- Vitest
- Tailwind
- Turborepo
- Amazon Bedrock
- Shadcn/UI
- TanStack Query
- Effect
- TanStack Router
- AWS STS
- pnpm
Возможные вопросы на собеседовании
Проверка практического опыта работы с ограничениями контекстного окна и выбора между RAG и инструментами.
Как вы принимаете решение о том, стоит ли включать знания непосредственно в промпт, использовать RAG или предоставить агенту инструмент для выполнения кода?
Важно для обеспечения безопасности при выполнении сгенерированного ИИ кода.
Какие стратегии вы бы использовали для обеспечения безопасности и изоляции при выполнении кода, сгенерированного LLM, в многопользовательской среде?
Проверка владения основным технологическим стеком команды.
Каков ваш опыт работы с экосистемой Effect или строго типизированным функциональным программированием в TypeScript?
Оценка понимания жизненного цикла разработки и эксплуатации ИИ-систем.
Расскажите о наиболее сложном случае отказа LLM в вашей практике: как вы его обнаружили и как изменили архитектуру системы для предотвращения подобных случаев?
Проверка навыков проектирования масштабируемых систем.
Как бы вы спроектировали систему обнаружения и вызова навыков (skills) для агента, если их количество исчисляется сотнями?
Похожие вакансии
AI Engineer (CV & Navigation)
Senior / Lead LLM Engineer
Middle, Middle+, Senior GenAI/LLM Разработчик
Senior Python AI Developer
GenAI/LLM Разработчик
Middle / Senior GenAI Engineer (CV)
1000+ офферов получено
Устали искать работу? Мы найдём её за вас
Quick Offer улучшит ваше резюме, подберёт лучшие вакансии и откликнется за вас. Результат — в 3 раза больше приглашений на собеседования и никакой рутины!
- Страна
- Грузия