AI Engineer

Phoeniqs Technologies; Basel; Vor Ort; CHF 120.000 - 180.000; Vollzeit

Zusammenfassung

Phoeniqs Technologies is seeking a forward‑thinking AI Developer to design, build, and scale agentic systems capable of multi-step reasoning, tool usage, and autonomous action. You will develop production-grade agentic AI with modular workflows and robust prompting strategies.

Join a team delivering cutting-edge AI solutions, collaborating with Product, Engineering, Data Science, and UX to push the frontier of agent-driven software in Basel.

Qualifikationen

• 3+ years in Software Engineering or Applied AI.
• Strong Python skills.
• Hands-on experience with agent frameworks such as LangChain, DSPy, AutoGen, CrewAI (or equivalent).
• Deep understanding of agent design patterns: Planner/Executor, Memory & Reflection loops, Tool selection, Self-evaluation.
• Expertise in prompt engineering, including: Chain‑of‑Thought, ReAct, Structured prompting, Output validation.
• Experience building RAG systems: Chunking strategies Embedding optimization Retrieval tuning.
• Experience with vector DBs: FAISS, Pinecone, Weaviate, OpenSearch.
• LLM deployment via APIs or open-source models (e.g. LLaMA, Mistral, Qwen, DeepSeek).
• Familiarity with inference frameworks: vLLM, TGI, Ollama.
• Tool integration experience: REST APIs, Databases, File systems, Browser automation.
• Working knowledge of: Docker, Git, AWS / GCP / Azure.

Aufgaben

• Architect and develop agentic AI systems using frameworks like LangChain, AutoGen, DSPy, CrewAI or custom orchestration layers.
• Design modular, goal-oriented workflows for autonomous task planning and inter-agent collaboration.
• Implement advanced agent patterns including Planner–Executor loops, ReAct, Reflection & Self‑Verification.
• Engineer sophisticated prompting strategies: Chain-of-Thought, Tree-of-Thought, Structured outputs, Prompt versioning.
• Build persistent memory systems (short-term, long-term, episodic).
• Integrate LLMs with execution environments: Python, Bash, SQL, REST APIs, Browser automation.
• Design and optimize RAG pipelines with vector databases and hybrid search.
• Implement API orchestration, tool calling, and code execution agents.
• Deploy scalable AI systems using Docker, CI/CD, and cloud platforms.
• Monitor agent behavior, execution traces, and reasoning paths.
• Implement human-in-the-loop workflows to ensure safe autonomy.
• Collaborate with Product, Engineering, Data Science, and UX teams.

Kenntnisse

Python

LangChain

DSPy

AutoGen

CrewAI

Prompt engineering

LLM APIs

Vector databases

Docker

Git

Cloud platforms

Tools

FAISS

Pinecone

Weaviate

OpenSearch

Docker

Git

AWS

GCP

Azure

Jobbeschreibung

AI Developer (Agentic Systems)

Phoeniqs Technologies | Build the Future of Autonomous Intelligence

At Phoeniqs Technologies , we’re not just integrating AI into systems — we’re engineering intelligence that can think, plan, collaborate, and act.

We’re looking for a forward-thinking AI Developer to help us design and scale the next generation of goal-driven, autonomous AI agents capable of multi‑step reasoning, tool usage, and continuous self‑improvement. If you’re passionate about agent architectures, prompt engineering, and modular AI orchestration — and want to ship real-world AI systems that actually do things — this is your role.

What You’ll Be Building

You’ll work at the frontier of applied AI, developing production-grade agentic systems that can:

• Make decisions
• Plan and execute complex tasks
• Collaborate with other agents
• Learn from memory
• Interact with tools, APIs, and real-world environments

From research agents to coding copilots and planning assistants — your work will power intelligent systems that move from response-based AI → action-based autonomy.

Your Impact

• Architect and develop agentic AI systems using frameworks like LangChain, AutoGen, DSPy, CrewAI or custom orchestration layers
• Design modular, goal-oriented workflows for autonomous task planning and inter-agent collaboration
• Implement advanced agent patterns including:
  • Planner–Executor loops
  • ReAct
  • Reflection & Self‑Verification
• Engineer sophisticated prompting strategies:
  • Chain-of-Thought
  • Tree-of-Thought
  • Structured outputs
  • Prompt versioning
• Build persistent memory systems (short-term, long-term, episodic)
• Integrate LLMs (OpenAI, Anthropic, Cohere, Mistral, DeepSeek, OSS models) with execution environments:
  • Python
  • Bash
  • SQL
  • REST APIs
  • Browser automation
• Design and optimize RAG pipelines with vector databases and hybrid search
• Implement API orchestration, tool calling, and code execution agents
• Deploy scalable AI systems using Docker, CI/CD, and cloud platforms
• Monitor agent behavior, execution traces, and reasoning paths
• Implement human-in-the-loop workflows to ensure safe autonomy
• Collaborate with Product, Engineering, Data Science, and UX teams to deliver high-impact AI solutions

What You Bring

• 3+ years in Software Engineering or Applied AI
• Strong Python skills
• Hands-on experience with agent frameworks such as: LangChain, DSPy, AutoGen, CrewAI (or equivalent)
• Deep understanding of agent design patterns:, Planner/Executor, Memory & Reflection loops, Tool selection, Self-evaluation
• Expertise in prompt engineering, including: Chain‑of‑Thought, ReAct, Structured prompting, Output validation
• Experience building RAG systems : Chunking strategies Embedding optimization Retrieval tuning
• Experience with vector DBs: FAISS, Pinecon ,Weaviate, OpenSearch
• LLM deployment via APIs or open-source models (e.g. LLaMA, Mistral, Qwen, DeepSeek)
• Familiarity with inference frameworks: vLLM, TGI, Ollama
• Tool integration experience: REST APIs, Databases, File systems, Browser automation
• Working knowledge of: Docker, Git, AWS / GCP / Azure

Bonus Points

• Built AI copilots, taskbots, or autonomous agents in production
• Experience with observability & safety tooling:
  • Guardrails AI
  • Rebuff
  • HoneyHive
• Model routing & dynamic model selection
• Context window optimisation
• Fine-tuning techniques (LoRA, QLoRA)
• Contributions to open-source agent or LLM tooling
• Familiarity with:
  • Prompt injection mitigation
  • Alignment strategies
  • AI safety best practices

Why Phoeniqs?

At Phoeniqs Technologies, you’ll work on cutting-edge AI systems that move beyond chat into execution and autonomy. We believe the future of software is agent-driven , and we’re building the orchestration layer that makes it real.

If you’re excited by the idea of AI systems that don’t just assist — but act — we’d love to meet you.