ai engineer for LLM applications

HireHi; United States; Remote; USD 150,000 - 190,000; Full time

Job summary

HireHi ищет опытного инженера ML/LLM для разработки корпоративного ПО и решений с использованием RAG, чат-ботов и автономных рабочих процессов. Вы будете проектировать архитектуры с использованием эмбеддингов, векторных баз данных и инструментов оркестрации LLM.

Кандидат обладает 3+ годами практического опыта, знаком с OpenAI/Anthropic и облачными платформами, владеет Python на продвинутом уровне и способен проектировать надёжные системы с учётом себестоимости и задержек.

Qualifications

• 3+ года опыта разработки ПО/ML и внедрения LLM-приложений.
• Доказанный опыт доставки end-to-end применяемых AI-систем.
• Продвинутый уровень Python и знание LLM/APIs.
• Опыт построения RAG-подходов с эмбеддингами и векторными БД.

Responsibilities

• Проектировать и поставлять продакшн-приложения на LLM, включая чаты и авто‑рабочие процессы.
• Строить и внедрять RAG‑пipelines с частями по chunking, embeddings и векторным поиском.
• Разрабатывать агентные архитектуры с многоступенчатым рассуждением и вызовами функций.
• Автоматизировать бизнес‑и инженерные процессы через агентный AI и workflow‑автоматику.
• Разрабатывать стратегии подсказок, тестов и обеспечивать качество,_latency, и стоимость.

Skills

Python

LLM APIs

RAG-подходы

Agentic AI

English (B2+)

Tools

Pinecone

Qdrant

Milvus

pgvector

Docker

Kubernetes

Job description

Описание

The company develops enterprise software products, open source solutions, and accelerators.

Задачи

Architect and deliver production LLM applications, including chat, copilots, assistants, and autonomous workflows; Construct and implement RAG pipelines with chunking, embeddings, vector search, reranking, and grounding; Create agentic architectures with multi-step reasoning, tool and function calling, planning, memory, and multi-agent orchestration; Support the automation of business and engineering workflows through agentic AI and workflow automation; Establish prompt and context strategies, construct evaluation harnesses, and maintain quality, latency, and cost standards; Connect LLMs with internal data, APIs, and tools through connectors, function calling, and structured outputs; Deploy guardrails, safety, and observability for AI systems, including tracing, evaluations, and quality and drift monitoring; Partner with product, data, and platform teams to transform ambiguous problems into shipped AI features; Exchange knowledge with fellow engineers and take part in design reviews.

Требования

3+ Years of software or ML engineering experience, including recent hands-on experience building and shipping LLM applications; Demonstrated track record of delivering applied-AI systems end to end; Advanced Python proficiency; Experience building RAG systems with embeddings, retrieval, reranking, and vector databases such as Pinecone, Qdrant, Milvus, or pgvector; Expertise in LLM APIs and orchestration frameworks such as OpenAI, Anthropic, LangChain, or LlamaIndex; Experience designing production agentic architectures with tool use, function calling, planning loops, and agent orchestration; Competence in automating workflows with agentic AI or workflow-automation tooling; Knowledge of prompt engineering and structured/JSON output techniques; Ability to design evaluations and reason about LLM quality, cost, and latency trade-offs at scale; Strong written and spoken English at B2+ level; Nice to have: familiarity with multi-agent frameworks such as LangGraph, CrewAI, or AutoGen; background in fine-tuning, adapters such as LoRA, or model distillation; understanding of MLOps/LLMOps, including deployment, versioning, monitoring, model serving, and inference optimization; knowledge of AI safety, guardrails, and evaluation frameworks such as Ragas, LangSmith, or promptfoo; expertise in cloud platforms such as AWS, GCP, or Azure and containerization with Docker or Kubernetes.

Условия

Remote work is available in Georgia and Armenia.