Infosys Nova Holdings LLC is hiring an AI Engineer in Charlotte, NC for an onsite role. In this position, you will help build secure, production-ready AI services and agentic workflows that support measurable business outcomes, from retrieval and model integration to operations and delivery practices.
What you’ll do
- Design and implement production-grade AI applications, copilots, and agentic workflows tied to measurable business results.
- Build maintainable Python services and expose AI capabilities through secure, versioned FastAPI interfaces.
- Develop retrieval-augmented generation (RAG) pipelines including ingestion, chunking, metadata, embeddings, retrieval, reranking, citation, and evaluation.
- Integrate and invoke LLMs using provider SDKs or model gateways, applying structured outputs, tool or function calling, retries, rate limits, token controls, and fallbacks.
- Use LangGraph to implement stateful, controllable workflows and apply LangChain selectively for model, tool, retriever, and prompt integrations.
- Bring hands-on experience with Model Context Protocol (MCP), including building or integrating MCP servers and MCP clients.
- Expose enterprise capabilities through MCP tools, resources, and prompts with appropriate schemas and controls.
- Create and run Apache Airflow DAGs for scheduled ingestion, embedding refresh, evaluation, batch processing, and data quality controls.
- Design MongoDB document models, indexes, and access patterns for application state, conversation history, metadata, and operational records.
- Implement automated testing and CI/CD, plus infrastructure configuration, logging, tracing, monitoring, and incident-ready runbooks.
- Collaborate with product owners, data engineers, security, architecture, and subject-matter experts to translate requirements into safe technical designs.
- Document architecture decisions, model limitations, data lineage, controls, and support procedures.
What you’ll need
- Typically 4+ years of software, data, or machine-learning engineering experience, including at least 1 year delivering LLM-enabled applications (shipped products with equivalent depth are acceptable).
- Demonstrated ownership of at least one AI solution beyond proof of concept, with production evidence such as monitoring, security controls, evaluation, support, and measurable outcomes.
- Bachelor’s degree in computer science, engineering, mathematics, or a related discipline, or equivalent professional experience.
- For a senior appointment: evidence of technical design leadership, mentoring, architecture decisions, and cross-team delivery.
- Experience with model gateways and providers including Azure OpenAI, Anthropic, or AWS Bedrock.
- Experience with vector search platforms or extensions such as MongoDB Vector Search, Elasticsearch/OpenSearch, or Milvus.
- MLOps/LLMOps tooling for prompt and version management, experiment tracking, evaluation, and tracing (for example, Galileo).
- Cloud-native delivery using RedHat OpenShift or equivalent infrastructure as code.
- Knowledge-graph, multimodal, fine-tuning, synthetic-data, or advanced agent-evaluation experience.
- Experience working in regulated or control-focused environments with formal architecture, risk, privacy, and change-management processes.
- Essential technical skills: Python, FastAPI & APIs, Apache, RAG, LLM, LangGraph, LangChain, MongoDB.
Core technologies
- Python, FastAPI, Apache Airflow
- RAG, LLM APIs
- LangGraph, LangChain
- MongoDB, MongoDB Vector Search
- Model Context Protocol (MCP), MCP servers, MCP clients
- Azure OpenAI, Anthropic, AWS Bedrock
- Elasticsearch, OpenSearch, Milvus
- Galileo
- RedHat OpenShift
Location: Charlotte, NC (onsite). Compensation: USD 100,000 - 115,000 per year. Experience: typically 4+ years.