AI Engineer

ph3AI Developer (Agentic Systems) /h3h3Phoeniqs Technologies | Build the Future of Autonomous Intelligence /h3pAt bPhoeniqs Technologies /b, we’re not just integrating AI into systems — we’re engineering intelligence that can think, plan, collaborate, and act. /ppWe’re looking for a bforward-thinking AI Developer /b to help us design and scale the next generation of bgoal-driven, autonomous AI agents /b 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. /ph3What You’ll Be Building /h3pYou’ll work at the frontier of applied AI, developing production-grade agentic systems that can: /pulliMake decisions /liliPlan and execute complex tasks /liliCollaborate with other agents /liliLearn from memory /liliInteract with tools, APIs, and real-world environments /li /ulpFrom research agents to coding copilots and planning assistants — your work will power intelligent systems that move from bresponse-based AI → action-based autonomy /b. /ph3Your Impact /h3ulliArchitect and develop agentic AI systems using frameworks like LangChain, AutoGen, DSPy, CrewAI or custom orchestration layers /liliDesign modular, goal-oriented workflows for autonomous task planning and

inter-agent collaboration /liliImplement advanced agent patterns including:ulliPlanner–Executor loops /liliReAct /liliReflection Self‑Verification /li /ul /liliEngineer sophisticated prompting strategies:ulliChain-of-Thought /liliTree-of-Thought /liliStructured outputs /liliPrompt versioning /li /ul /liliBuild persistent memory systems (short-term, long-term, episodic) /liliIntegrate LLMs (OpenAI, Anthropic, Cohere, Mistral, DeepSeek, OSS models) with execution environments:ulliPython /liliBash /liliSQL /liliREST APIs /liliBrowser automation /li /ul /liliDesign and optimize RAG pipelines with vector databases and hybrid search /liliImplement API orchestration, tool calling, and code execution agents /liliDeploy scalable AI systems using Docker, CI/CD, and cloud platforms /liliMonitor agent behavior, execution traces, and reasoning paths /liliImplement human-in-the-loop workflows to

ensure safe autonomy /liliCollaborate with Product, Engineering, Data Science, and UX teams to deliver high-impact AI solutions /li /ulh3What You Bring /h3ulli3+ years in Software Engineering or Applied AI /liliStrong Python skills /liliHands-on experience with agent frameworks such as: LangChain, DSPy, AutoGen, CrewAI (or equivalent) /liliDeep understanding of agent design patterns:, Planner/Executor, Memory Reflection loops, Tool selection, Self-evaluation /liliExpertise in prompt engineering, including: Chain‑of‑Thought, ReAct, Structured prompting, Output validation /liliExperience building RAG systems: Chunking strategies Embedding optimization Retrieval tuning /liliExperience with vector DBs: FAISS, Pinecon ,Weaviate, OpenSearch /liliLLM deployment via APIs or open-source models (e.g.

LLaMA, Mistral, Qwen, DeepSeek) /liliFamiliarity with inference frameworks: vLLM, TGI, Ollama /liliTool integration experience: REST APIs, Databases, File systems, Browser automation /liliWorking knowledge of: Docker, Git, AWS / GCP / Azure /li /ulh3Bonus Points /h3ulliBuilt AI copilots, taskbots, or autonomous agents in production /liliExperience with observability safety tooling:ulliGuardrails AI /liliRebuff /liliHoneyHive /li /ul /liliModel routing dynamic model selection /liliContext window optimisation /liliFine-tuning techniques (LoRA, QLoRA) /liliContributions to open-source agent or LLM tooling /liliFamiliarity with:ulliPrompt injection mitigation /liliAlignment strategies /liliAI safety best practices /li /ul /li /ulh3Why Phoeniqs? /h3pAt 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. /ppIf you’re excited by the idea of AI systems that don’t just assist — but act — we’d love to meet you. /p /p