Agentic AI Developer

Role: Agentic AI Developer

Location: Remote (Must be based out of East Coast only)

Job Description: Agentic AI Developer

Agentic AI Developer to design, build, and deploy AI agents capable of autonomous decision-making, task orchestration, and integration across complex enterprise environments. The ideal candidate will have hands-on experience with AI frameworks, multi-agent systems, and orchestration platforms. Experience in Agentic AI security, trust, and alignment will be considered a strong plus.

Key Responsibilities

• Design, develop, and deploy autonomous AI agents for business-critical use cases.
• Implement multi-agent collaboration frameworks for complex workflows.
• Integrate AI agents with enterprise systems, APIs, and external services.
• Leverage LLMs and specialized AI models to enable reasoning, planning, and execution.
• Optimize agent performance with respect to latency, cost, and scalability.
• Ensure alignment, explainability, and reliability of AI agents in production.
• (Optional) Develop and enforce Agentic AI security controls, including agent sandboxing, prompt injection defense, adversarial robustness, and monitoring frameworks.
• Collaborate with data scientists, engineers, and product managers to identify opportunities and build agentic AI solutions.
• Stay current with advancements in LLMs, multi-agent systems, and AI safety research.

Required Qualifications

• Strong programming skills in Python (experience with LangChain, LlamaIndex, or similar frameworks preferred).
• Experience building and deploying applications with LLMs (OpenAI, Anthropic, LLaMA, Mistral, etc.).
• Knowledge of autonomous agent architectures, planning algorithms, or workflow orchestration.
• Familiarity with cloud platforms (AWS, Azure, Google Cloud Platform) and containerization (Docker, Kubernetes).
• Understanding of vector databases (Pinecone, Weaviate, FAISS, Milvus, etc.).
• Ability to apply prompt engineering and fine-tuning techniques for specialized tasks.
• Strong problem-solving and analytical skills.

Preferred / Optional Qualifications

• Experience in Agentic AI Security, including:
  • Secure prompt design and injection prevention.
  • Agent governance, monitoring, and fail-safe mechanisms.
  • Adversarial testing and red-teaming of agent behaviors.
  • Knowledge of AI alignment and responsible AI frameworks.
• Familiarity with reinforcement learning and planning algorithms (e.g., ReAct, AutoGPT, BabyAGI-style architectures).
• Contributions to open-source AI projects or research in multi-agent systems