Yodaplus
Website:
yodaplus.com
Job details:
The Opportunity
We are looking for a hands-on AI/GenAI Engineer to design, develop, and deploy production-grade AI solutions. The role involves building LLM applications, RAG pipelines, and agentic AI systems, integrating them into enterprise platforms while ensuring scalability, reliability, security, and performance.
Location - United States of America
MUST HAVE - Currently on valid H1B or on OPT and looking for visa transfer
Key Responsibilities
- Design, develop, test, deploy, and maintain production-grade AI/ML and GenAI solutions.
- Build LLM applications, RAG pipelines, and single-agent and multi-agent systems.
- Translate business requirements into scalable technical architectures, APIs, and workflows.
- Develop and integrate AI capabilities into enterprise applications and data platforms.
- Troubleshoot and optimize AI systems for performance, reliability, and cost.
- Implement testing, evaluation, monitoring, and security best practices.
- Collaborate with engineering, product, architecture, and business teams.
- Leverage AI coding tools such as Claude Code, Codex, and GitHub Copilot to accelerate development.
Required Technical Skills
Generative AI & RAG
- Experience building production LLM applications using Azure OpenAI, AWS Bedrock, or Google Vertex AI.
- Strong understanding of RAG architectures, embeddings, vector databases, semantic search, and prompt engineering.
- Experience with LangChain, LlamaIndex, Pinecone, pgvector, Azure AI Search, or similar technologies.
Agentic AI & LLMOps
- Experience building agentic workflows, tool-calling systems, and multi-agent orchestration using LangGraph, CrewAI, AutoGen, or similar frameworks.
- Understanding of agent memory, context management, retries, fallbacks, and error handling.
- Experience with LLM evaluation, debugging, and quality assessment using frameworks such as RAGAS, DeepEval, or Arize Phoenix.
Software Engineering & Cloud
- Strong Python programming skills and experience developing production-quality applications.
- Experience with REST APIs, asynchronous programming, microservices, and enterprise integrations.
- Familiarity with Docker, Kubernetes, AWS ECS, or Azure Container Apps.
- Experience handling structured and unstructured data, data pipelines, and software testing.
Professional Skills & Qualifications
- Strong problem-solving, debugging, and analytical skills.
- Ability to communicate technical concepts to business and technical stakeholders.
- Ownership of solutions from design through production deployment.
- Ability to work collaboratively in fast-changing environments.
- Understanding of enterprise security, governance, and compliance requirements.
- 2+ years of software engineering experience, including hands-on AI/ML development.
- Bachelor's degree preferred.
Good to Have
- LLM observability and monitoring tools such as LangSmith, Arize, or Datadog.
- Experience with LLM fine-tuning techniques such as LoRA, QLoRA, and PEFT.
- Knowledge of inference optimization for latency, throughput, and cost.
- Understanding of AI security, prompt injection prevention, and responsible AI practices.
- Experience with cloud ML platforms such as Azure ML, AWS SageMaker, or Vertex AI.
- Exposure to AI solutions for financial services or other regulated industries.
Click on Apply to know more.