AI Engineer

At Phoeniqs Technologies we engineer autonomous intelligence that can think, plan, collaborate and act. As an AI Engineer you will join a team that builds goal‑driven agents capable of multi‑step reasoning, tool usage and continuous self‑improvement, turning research‑grade concepts into production‑grade systems that move beyond chat‑only AI. Your daily work will revolve around designing and implementing agentic pipelines. You will architect modular workflows with frameworks such as LangChain, AutoGen, DSPy or CrewAI, and create Planner‑Executor loops, ReAct and reflection patterns. Prompt engineering will be central, you'll craft Chain‑of‑Thought, Tree‑of‑Thought and structured outputs, while managing versioned prompts. You'll build persistent memory layers, integrate large language models from providers like OpenAI, Anthropic or open‑source alternatives, and connect them to execution environments (Python, Bash, SQL, REST APIs, browser automation). RAG pipelines will be tuned with vector databases, and you'll containerise and deploy the resulting services using Docker, CI/CD and cloud platforms, monitoring execution traces and adding human‑in‑the‑loop safeguards. The role requires solid software engineering foundations and applied AI experience. You must have at least three years of professional work in software or AI, strong Python proficiency, and hands‑on experience with agent frameworks such as LangChain, DSPy, AutoGen or CrewAI. Deep knowledge of agent design patterns, including planner/executor cycles, memory and reflection loops, and tool selection, is essential, as is expertise in advanced prompt engineering techniques like Chain‑of‑Thought and ReAct. You should also be comfortable building retrieval‑augmented generation systems and working with vector stores such as FAISS, Pinecone, Weaviate or OpenSearch, as well as deploying LLMs via APIs or open‑source models and using inference runtimes like vLLM, TGI or Ollama. Familiarity with Docker, Git and major cloud providers (AWS, GCP, Azure) rounds out the core skill set. Additional strengths are welcomed. Candidates who have shipped AI copilots, task‑bots or autonomous agents in production will stand out, as will experience with observability and safety tooling such as Guardrails AI or HoneyHive. Knowledge of model routing, context‑window optimisation, fine‑tuning methods (LoRA, QLoRA) and contributions to open‑source agent or LLM projects are also valued. Phoeniqs offers a fast‑moving environment where you will collaborate closely with product, engineering, data science and UX teams, shaping the future of agent‑driven software. What the role asks for: - 3+ years in Software Engineering or Applied AI - Strong Python skills - Experience with agent frameworks (LangChain, DSPy, AutoGen, CrewAI) - Expertise in prompt engineering (Chain‑of‑Thought, ReAct, Structured prompting) - Experience with vector DBs (FAISS, Pinecone, Weaviate, OpenSearch) - Nice-to-have, built AI copilots or autonomous agents in production - Nice-to-have, experience with observability & safety tooling (Guardrails AI, Rebuff) - Nice-to-have, familiarity with fine‑tuning techniques (LoRA, QLoRA)