Agentic AI Engineer
- VKore Solutions LLC
2 Days Ago
NA
C2C
San Jose-CA
8-12 Years
Required Skills: Python, Building LLM-powered applications, Agentic AI Architecture, REST APIs, microservices, Git, Docker, CI/CD, PostgreSQL, MongoDB, SQL Server
Job Description
We are seeking an experienced Agentic AI Engineer to design, develop, and deploy intelligent AI agents and multi-agent systems that can autonomously reason, plan, use tools, interact with enterprise systems, and execute complex workflows.
The ideal candidate will have strong hands-on experience with Generative AI, LLMs, RAG, AI agents, Python, LLM orchestration frameworks, APIs, and cloud platforms, along with a solid understanding of production-grade AI/ML engineering.
Key Responsibilities
- Design and build agentic AI applications and autonomous AI agents using LLMs.
- Develop multi-agent architectures for complex business workflows.
- Implement agent capabilities including reasoning, planning, tool/function calling, memory, reflection, and task execution.
- Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, vector search, retrieval, and reranking.
- Integrate LLMs such as OpenAI, Anthropic, Google Gemini, or Azure OpenAI into enterprise applications.
- Work with frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or equivalent agent orchestration technologies.
- Develop APIs and backend services using Python, FastAPI, REST, and microservices.
- Integrate AI agents with enterprise databases, SaaS platforms, APIs, and business applications.
- Implement short-term and long-term agent memory and context management.
- Develop evaluation frameworks to measure agent accuracy, reliability, latency, and cost.
- Implement guardrails, security controls, observability, and responsible AI practices.
- Deploy and operate AI solutions on AWS, Azure, or GCP.
- Collaborate with data scientists, ML engineers, software engineers, product managers, and business stakeholders.
Required Skills
- Strong proficiency in Python.
- Hands-on experience building LLM-powered applications and AI agents.
- Strong understanding of Agentic AI architecture and design patterns.
- Experience with LLM orchestration frameworks, preferably LangChain/LangGraph or similar.
- Experience with RAG, embeddings, vector databases, and semantic search.
- Experience with LLM APIs, prompt engineering, function/tool calling, and structured outputs.
- Strong knowledge of REST APIs, microservices, Git, Docker, and CI/CD.
- Experience with databases such as PostgreSQL, MongoDB, SQL Server, or similar.
- Experience with vector stores such as Pinecone, Weaviate, Milvus, Chroma, FAISS, or pgvector.
- Experience deploying AI applications to AWS, Azure, or GCP.
- Understanding of LLM evaluation, hallucination mitigation, security, and AI governance.
Preferred Skills
- Experience with multi-agent systems.
- Experience with MCP (Model Context Protocol) and agent tool ecosystems.
- Experience with agent memory, workflow orchestration, and human-in-the-loop systems.
- Knowledge of knowledge graphs and GraphRAG.
- Experience with Kubernetes and cloud-native deployments.
- Familiarity with ML frameworks such as PyTorch or TensorFlow.
- Experience with observability/evaluation platforms such as LangSmith, Arize, Langfuse, or equivalent.
- Experience working with enterprise-scale AI implementations.
Education
Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related technical discipline.
Ideal Candidate
The successful candidate is a hands-on AI engineer who can take an Agentic AI concept from architecture and proof-of-concept through production deployment, while balancing model quality, scalability,
