AI Engineer
Opsfleet · AI services
unknownRemote
Salary Range (USD)
Negotiable
Location
Location N/A
Visa Support
Not mentioned
Funding Stage
Unknown
Job Responsibilities
- • Build production LLM agents for clients, including multi‑agent systems, tool use and retrieval‑augmented generation (RAG)
- • Develop agents in Python on AWS Bedrock and GCP Vertex AI
- • Maintain direct client contact throughout projects
- • Participate in interview process: intro call, take‑home assignment, technical interview
Required Skills
Built and shipped LLM agents to productionExperience with frameworks such as Strands Agents, LangChain, Agno, Deep Agents, Google ADK or Claude Agent SDKProficient in PythonFamiliarity with AWS Bedrock and GCP Vertex AIStrong communication and collaboration skillsAbility to take ownership of projects
Engineering Culture & Tech Stack
PythonAWS BedrockGCP Vertex AILangChainStrands AgentsAgnoDeep AgentsGoogle ADKClaude Agent SDK
communicative
collaborative
eager to learn
ownership
Raw Post
Show original text
Opsfleet | AI Engineer (Agentic / GenAI) | REMOTE (EEA) | Full-time
Fully remote cloud & AI services company (founded 2015, 70+ engineers, AWS Premier, Google Cloud & Snowflake Partner) with a growing GenAI practice and several active client projects.
You'll build production LLM agents for clients: multi-agent systems, tool use and RAG, in Python, on AWS Bedrock and GCP Vertex AI. Direct client contact.
We're looking for a hands-on engineer (not a research or prompt-only role) who has built and shipped LLM agents to production, with frameworks like Strands Agents, LangChain, Agno, Deep Agents, Google ADK or Claude Agent SDK.
Just as important: we hire good people. Communicative, collaborative, eager to learn and happy to take ownership. That's what makes people succeed here, with clients and with the team.
Process: intro call -> take-home assignment -> technical interview -> offer.
Apply: https://www.linkedin.com/jobs/view/4478769287/ or hiring@opsfleet.com, please mention HN
AI Risk Insights
No major risk signals detected.
Recent News
No recent updates
Data Source
Content parsed by LLM from Hacker News raw data. Confidence:HIGH