Senior AI Agentic Engineer

What You’ll Be Doing

• Lead the design, development, and deployment of autonomous AI agents capable of multi-step reasoning and planning.

• Architect scalable memory and retrieval systems using vector databases and embeddings to provide long-term context.

• Build and optimize agent orchestration workflows using techniques like ReAct, Chain-of-Thought, and LangGraph.

• Collaborate cross-functionally with research, product, and engineering teams to define AI agent capabilities and roadmaps.

• Drive prompt engineering, fine-tuning, and continual performance improvements of AI agents.

• Ensure AI safety by implementing monitoring, observability, and risk mitigation strategies.

• Mentor and support junior engineers, reviewing code and sharing best practices.

• Oversee cloud infrastructure, containerization, and CI/CD pipelines to ensure scalable, reliable deployments.

What You Should Bring

• Deep expertise in Python and AI/ML system development with a strong focus on autonomous agents.

• Hands-on experience with LLM APIs such as OpenAI GPT-4, Anthropic Claude, or Google Gemini.

• Proficiency with agent frameworks like LangChain, AutoGPT, or CrewAI.

• Strong knowledge of vector databases (FAISS, Pinecone) and embedding models.

• Skilled in prompt engineering and designing multi-agent workflows.

• Product mindset with focus on real-world impact and usability.

• Proven leadership experience including mentoring and collaborating with cross-functional teams.

• Commitment to AI safety, reliability, and ethical considerations.

• Strong debugging and problem-solving skills, especially when dealing with unpredictable model outputs or complex agent behavior.

• Attention to detail around safety and reliability, including awareness of risks like prompt injection, hallucination, and misuse.

• Strong communication and collaboration skills to work effectively across multiple teams.

• A proactive, growth-oriented mindset with a high level of intellectual curiosity.

• Solid understanding of SDLC, CI/CD, and agile methodologies.

• Commitment to writing secure, performant, and accessible code.

Required Skills

• Advanced Python programming skills for AI/ML applications.

• Extensive experience with LLM APIs and agentic AI frameworks.

• Expertise in vector databases and retrieval-augmented generation (RAG).

• Mastery of prompt engineering techniques: few-shot, CoT, and function calling.

• Experience integrating external tools and APIs into AI agents.

• Knowledge of web frameworks like FastAPI or Flask.

• Proficiency with Docker, Kubernetes, and cloud platforms (AWS, GCP, Azure).

• Strong debugging, logging, and monitoring skills for AI systems.

• Excellent communication and leadership capabilities.

Preferred Skills

• Experience with reinforcement learning or multi-agent systems.

• Background in fine-tuning LLMs or prompt tuning at scale.

• Contributions to open-source AI projects or published research.

• Familiarity with AI safety frameworks and bias mitigation strategies.

• Proficiency with experiment tracking tools like Weights & Biases or LangSmith.

AI-Enhanced Development

• Leverage AI tools like GitHub Copilot to accelerate development workflows, improve code quality, and reduce boilerplate.

• Demonstrate proficiency in prompt engineering to effectively guide AI tools in generating optimal and context-aware code solutions.

• Use AI-assisted pair programming to support rapid prototyping, test case generation, and debugging.

• Stay informed about the evolving landscape of AI-powered development tools and integrate best practices into day-to-day engineering work.

  • Encourage and mentor team members on responsible and secure use of AI in the software development lifecycle.