R&D Engineering, Sr Engineer

Role overview

Agentic AI and retrieval

• Design, build, test, and deploy agentic applications using frameworks such as ADK, NAT, LangGraph, LangChain, CrewAI, and OpenCode for planning and multi-step orchestration.
• Implement semantic, procedural, episodic, working, session, and long-term agent memory with consolidation and retrieval strategies.
• Build RAG pipelines using embeddings, vector search, hybrid retrieval, reranking, and contextual grounding.
• Integrate agents with APIs, tools, databases, and search systems using function calling, MCP, and connector patterns.

Application quality and impact

• Develop backend services, orchestration layers, REST APIs, user-facing components, human-in-the-loop experiences, and operational dashboards.
• Build automated evaluations for answer quality, memory relevance, tool use, trajectory quality, hallucination rates, latency, cost, and safety.
• Implement tracing, structured logging, prompt versioning, model tracking, workflow telemetry, and incident analysis.
• Automate complex EDA workflows, reduce repetitive engineering tasks, and deliver production AI applications trusted by engineering teams.
• Establish reusable engineering patterns and improve AI quality and safety through evaluation frameworks, guardrails, and observability.
• Contribute through code reviews, design discussions, mentorship, and knowledge sharing; support secure, reliable, responsible AI deployment.

Required qualifications

• Bachelor's or Master's degree in Computer Science, Electrical Engineering, Data Science, or AI/ML, or equivalent practical experience.
• At least 2 years of software-engineering experience shipping production systems, including demonstrated AI/ML, Generative AI, or agentic AI application delivery.
• Strong Python proficiency and working knowledge of at least one of JavaScript, TypeScript, Java, C++, or Go.
• Hands-on experience with one or more agentic frameworks such as ADK, NAT, LangGraph, AutoGen, CrewAI, or Semantic Kernel, or equivalent technologies.
• Strong understanding of LLM application design, orchestration, prompt engineering, tool/function calling, RAG and hybrid Graph/RAG, agent memory, and single- and multi-agent patterns.
• Experience with vector databases, embeddings, search, reranking, and knowledge-retrieval pipelines for RAG and semantic search.

Additional pluses

• Full-stack AI application development, testing and evaluation of non-deterministic AI systems, AWS/GCP/Azure, Docker, Kubernetes, Git, CI/CD, automated testing, and Agile practices are strong pluses.
• Familiarity with AI observability, security, privacy, guardrails, and responsible AI principles is a strong plus.

Team and company

Rewards

• The employer describes health, wellness, and financial benefits; salary-range details are provided by a recruiter.